Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 4087
    Prev
    Next
    INDEX
    Explanations

    architect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sus
    -0.27
     spoilers
    -0.25
    ugal
    -0.25
     truth
    -0.25
    onaut
    -0.24
    uations
    -0.24
    orial
    -0.24
    缮çļĦåľ¨äºİ
    -0.24
    æłĩè®°
    -0.24
    .dataTables
    -0.24
    POSITIVE LOGITS
    _skin
    0.27
    _PATCH
    0.26
    anches
    0.25
    èĤ¢
    0.25
    ESCO
    0.25
    иÑĨе
    0.25
    _mv
    0.25
     anch
    0.24
    棻
    0.24
    .fil
    0.24
    Activations Density 0.031%

    No Known Activations