© 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. 43413
    Prev
    Next
    INDEX
    Explanations

    arthro

    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
    ivities
    -0.30
    IE
    -0.30
    iece
    -0.30
    ivel
    -0.30
    ie
    -0.29
    odem
    -0.28
    ä»ĭ
    -0.28
    ile
    -0.27
    ive
    -0.26
    ives
    -0.25
    POSITIVE LOGITS
    trap
    0.28
    踬
    0.28
    _MUT
    0.27
    ignet
    0.26
     cones
    0.26
    çľº
    0.25
    åħį
    0.25
    èŀºæĹĭ
    0.25
     trap
    0.24
    åĽĽä½į
    0.24
    Activations Density 0.002%

    No Known Activations