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. 24124
    Prev
    Next
    INDEX
    Explanations

    as

    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
    èĩªå·±çļĦ
    -0.28
    lage
    -0.28
    ç²Ł
    -0.28
    .jd
    -0.24
    irse
    -0.24
    åħ³æ³¨
    -0.24
    ahead
    -0.24
    lag
    -0.24
    èĩªèIJ¥
    -0.23
     cause
    -0.23
    POSITIVE LOGITS
    ÑģÑĤо
    0.27
    çĪ
    0.26
    ango
    0.25
    å¹³åİŁ
    0.24
    äºĭæķħåıijçĶŁ
    0.24
    çļĤ
    0.24
    .eval
    0.23
    asm
    0.23
    etta
    0.23
    ’h
    0.23
    Activations Density 0.003%

    No Known Activations