© 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. 39072
    Prev
    Next
    INDEX
    Explanations

    general news reporting

    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
     then
    -0.27
     dur
    -0.26
     entire
    -0.26
     current
    -0.25
     intended
    -0.24
    -nav
    -0.24
    éĤ£ä¹Ī
    -0.23
     inside
    -0.23
    /npm
    -0.23
    POSITIVE LOGITS
     fifty
    0.32
     Oswald
    0.30
    äºĶ大
    0.28
    oj
    0.27
    Ot
    0.27
    ô
    0.27
     Prosecutor
    0.27
    æĶ¹éĿ©åıijå±ķ
    0.26
    five
    0.26
    o
    0.26
    Activations Density 3.394%

    No Known Activations