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. 1487
    Prev
    Next
    INDEX
    Explanations

    aneurysms and medical topics

    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
     bitrate
    -0.26
    casting
    -0.25
     neo
    -0.24
    misc
    -0.24
     OTHERWISE
    -0.24
    stag
    -0.24
     entirely
    -0.23
    estring
    -0.23
    /compiler
    -0.23
    odcast
    -0.23
    POSITIVE LOGITS
    iktig
    0.29
    人å±ħ
    0.26
    auga
    0.26
    ynch
    0.26
    ãģĦãģĨ
    0.25
    æ·ĺ
    0.25
    çŁ¾
    0.25
    FUN
    0.25
    ableView
    0.25
     Regents
    0.24
    Activations Density 0.006%

    No Known Activations