© 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. 43226
    Prev
    Next
    INDEX
    Explanations

    diagnosis and determination

    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
    assist
    -0.29
    æ¶ĪåĮĸ
    -0.28
    chal
    -0.27
     cut
    -0.26
    Med
    -0.26
    ÑĢаб
    -0.26
    (Expression
    -0.25
    cut
    -0.25
    çĻ¾ä¸ĩ
    -0.25
     оÑĤзÑĭв
    -0.25
    POSITIVE LOGITS
     tá»ij
    0.33
     determining
    0.30
     determine
    0.29
     zero
    0.28
    è´°
    0.28
     ro
    0.28
     rule
    0.28
     determin
    0.27
     determinant
    0.27
    king
    0.26
    Activations Density 0.002%

    No Known Activations