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. 126021
    Prev
    Next
    INDEX
    Explanations

    toxicity

    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
    åĩºå¢ĥ
    -0.32
    åĮĿ
    -0.29
    æµģ失
    -0.26
    èĨı
    -0.25
    ($__
    -0.25
    mond
    -0.25
    NULL
    -0.25
    -null
    -0.25
    funcs
    -0.25
     ped
    -0.24
    POSITIVE LOGITS
    éŁ¿
    0.27
    fork
    0.27
    è¿©
    0.27
     AX
    0.24
    AX
    0.24
    AAD
    0.23
     PROPERTY
    0.23
    ãģķãģĪ
    0.23
    åħīåѦ
    0.23
     Trophy
    0.23
    Activations Density 0.042%

    No Known Activations