© 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. 39239
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ahan
    -0.28
    .writeValue
    -0.26
    inka
    -0.25
     useClass
    -0.25
     mú
    -0.23
    ast
    -0.23
    åIJĬ
    -0.23
     cÄĥ
    -0.23
    inosaur
    -0.23
    rost
    -0.23
    POSITIVE LOGITS
    -kind
    0.28
    æľīæŶ
    0.27
    occasion
    0.26
    æ¿ł
    0.25
    -Nov
    0.25
    æľīäºĽäºº
    0.25
    éģĩè§ģ
    0.25
    ħ§
    0.25
     bumped
    0.24
    æĦıè§ģ
    0.24
    Activations Density 0.010%

    No Known Activations