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. 7-TRANSCODER-HP
    4. 97985
    Prev
    Next
    INDEX
    Explanations

    forum posts and questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atives
    -0.29
    Then
    -0.27
    addle
    -0.27
    æįŁ
    -0.26
    æIJį
    -0.26
    éĤ£æł·çļĦ
    -0.26
    åģļå·¥
    -0.25
    Set
    -0.25
    hunt
    -0.25
     hardcoded
    -0.25
    POSITIVE LOGITS
    èģĮåĬ¡
    0.26
    åİĿ
    0.25
    (optarg
    0.24
    iage
    0.24
    æĶ¯çº¿
    0.24
    stairs
    0.24
    dere
    0.24
    ç¼Ĩ
    0.24
    èµ°
    0.24
    rait
    0.23
    Activations Density 0.000%

    No Known Activations