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. 23-TRANSCODER-HP
    4. 7476
    Prev
    Next
    INDEX
    Explanations

    informal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     formulations
    -0.31
    ç§įç±»
    -0.29
    ä¸Ģå¥Ĺ
    -0.29
    管çIJĨåĬŀæ³ķ
    -0.29
    åħ·ä½ĵæĥħåĨµ
    -0.28
    ofs
    -0.28
    ações
    -0.28
     formulas
    -0.28
    _specific
    -0.27
     какие
    -0.27
    POSITIVE LOGITS
     sco
    0.28
    oco
    0.26
     Bil
    0.25
    为代表
    0.24
    Bo
    0.24
    ho
    0.23
    AV
    0.23
     bo
    0.23
     option
    0.23
    èĥ«
    0.23
    Activations Density 0.000%

    No Known Activations