© 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. 39706
    Prev
    Next
    INDEX
    Explanations

    Euro

    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
    :`
    -0.27
    ä»Ģä¹Īåľ°æĸ¹
    -0.26
    Hmm
    -0.25
    åıĪ被
    -0.25
    å§ĵ
    -0.25
    ª
    -0.24
     prepend
    -0.24
    麽
    -0.24
    &&(
    -0.23
     paraph
    -0.23
    POSITIVE LOGITS
    l
    0.36
    su
    0.35
    v
    0.34
    sed
    0.33
    sa
    0.33
    b
    0.31
    g
    0.30
    gov
    0.29
    sheet
    0.29
    sol
    0.29
    Activations Density 2.123%

    No Known Activations