© 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. 39565
    Prev
    Next
    INDEX
    Explanations

    Json

    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
    SAT
    -0.34
    roken
    -0.29
    ulsive
    -0.28
    Sen
    -0.27
    dance
    -0.26
    kus
    -0.26
    Sz
    -0.25
    BLE
    -0.25
    Nine
    -0.25
    ospace
    -0.24
    POSITIVE LOGITS
    ï¼Į
    0.45
     æ
    0.41
     é
    0.38
     è
    0.38
    0.38
    ãĢĤ↵↵
    0.37
     ç
    0.37
     æł
    0.36
    ãĢĤč↵
    0.36
    .č↵
    0.36
    Activations Density 5.575%

    No Known Activations