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. 4082
    Prev
    Next
    INDEX
    Explanations

    children

    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
    ctors
    -0.25
     Disneyland
    -0.24
     ISBN
    -0.23
    rangle
    -0.23
     TRY
    -0.23
     SEN
    -0.23
     doll
    -0.23
    .IDENTITY
    -0.23
     Facts
    -0.23
    SSID
    -0.23
    POSITIVE LOGITS
    声
    0.30
    声éģĵ
    0.28
    ah
    0.28
    ziel
    0.27
     wholes
    0.27
    æ½ľåľ¨
    0.25
    宿
    0.25
    unner
    0.25
    ira
    0.25
     individual
    0.25
    Activations Density 0.042%

    No Known Activations