© 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. 42619
    Prev
    Next
    INDEX
    Explanations

    and

    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
    Another
    -0.33
    åı¦ä¸Ģä½į
    -0.31
     Another
    -0.30
     otra
    -0.29
    OTH
    -0.28
    åı¦
    -0.28
    -most
    -0.28
    Apps
    -0.27
    ymes
    -0.27
    ä½ľä¸ºä¸Ģç§į
    -0.26
    POSITIVE LOGITS
     nearly
    0.52
     almost
    0.44
     possible
    0.43
    åĩłä¹İ
    0.42
     potential
    0.40
    è¿ijä¹İ
    0.39
     virtually
    0.37
     practically
    0.37
    possible
    0.36
     probably
    0.33
    Activations Density 0.009%

    No Known Activations