© 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. 41775
    Prev
    Next
    INDEX
    Explanations

    Coding/Rules context

    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
    else
    -0.44
    ELSE
    -0.31
    Else
    -0.31
     ELSE
    -0.30
     else
    -0.29
     Else
    -0.28
     Ind
    -0.28
    .diag
    -0.27
    货车
    -0.27
    _else
    -0.27
    POSITIVE LOGITS
    Authority
    0.26
    -analysis
    0.26
     Desire
    0.26
    æłı
    0.25
    rpc
    0.25
     ApiController
    0.25
    ReturnValue
    0.25
    ulum
    0.25
    matchCondition
    0.24
     Discovery
    0.24
    Activations Density 0.012%

    No Known Activations