© 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. 35-TRANSCODER-HP
    7. 39160
    Prev
    Next
    INDEX
    Explanations

    technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     innoc
    -0.28
     viol
    -0.28
     yol
    -0.26
     Madden
    -0.26
     annot
    -0.26
     ell
    -0.26
    PLL
    -0.26
     mall
    -0.25
     evil
    -0.25
     fly
    -0.25
    POSITIVE LOGITS
    quest
    0.35
    oste
    0.34
    que
    0.33
    straight
    0.32
    asure
    0.31
    stor
    0.31
    iard
    0.30
    cause
    0.30
    serie
    0.30
    verse
    0.29
    Activations Density 0.010%

    No Known Activations