© 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. 33-TRANSCODER-HP
    7. 53955
    Prev
    Next
    INDEX
    Explanations

    next

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rides
    -0.31
     Holidays
    -0.30
     holidays
    -0.30
    åģĩæĹ¥
    -0.30
     holiday
    -0.29
    App
    -0.29
     tours
    -0.28
    zone
    -0.28
    å§Ķ
    -0.27
    ec
    -0.27
    POSITIVE LOGITS
    ustin
    0.30
    /lab
    0.29
    ocator
    0.27
    objs
    0.26
    ÑĦон
    0.25
    hon
    0.25
    å¦Ĥä½ķçľĭå¾ħ
    0.25
     affine
    0.24
     setObject
    0.24
     bú
    0.24
    Activations Density 0.071%

    No Known Activations