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. 24222
    Prev
    Next
    INDEX
    Explanations

    Seizure, voting, removal

    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
    æįŁ
    -0.26
    人次
    -0.26
    åľ°çIJĥä¸Ĭ
    -0.26
    ä¸Ģè§Ĵ
    -0.25
    åIJĥçļĦ
    -0.24
    ÂŃing
    -0.24
    çļĦåģļæ³ķ
    -0.24
     counselor
    -0.24
    athe
    -0.24
     Counseling
    -0.23
    POSITIVE LOGITS
    endant
    0.25
    Colon
    0.25
    麻éĨī
    0.25
    ä½ı
    0.25
    xygen
    0.24
    èѦ
    0.24
    .piece
    0.24
    ç·Ĭ
    0.23
    lectron
    0.23
    plier
    0.23
    Activations Density 0.003%

    No Known Activations