© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 41792
    Prev
    Next
    INDEX
    Explanations

    correlations and associations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     related
    -0.38
    -related
    -0.33
    related
    -0.33
     Related
    -0.31
    Related
    -0.30
    缸åħ³ä¿¡æģ¯
    -0.28
    缸åħ³çļĦ
    -0.28
    第ä¸Ģ书记
    -0.27
    BU
    -0.27
     principio
    -0.25
    POSITIVE LOGITS
     associations
    0.44
     correlations
    0.41
     possible
    0.40
     Associations
    0.38
     links
    0.37
     ties
    0.37
    possible
    0.33
     connections
    0.33
     Possible
    0.32
    Possible
    0.32
    Activations Density 0.004%

    No Known Activations