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. 11-TRANSCODER-HP
    4. 46739
    Prev
    Next
    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $",
    -0.30
    鸽
    -0.28
    $s
    -0.27
    çĤİ
    -0.26
    ovi
    -0.26
    celand
    -0.25
    indo
    -0.25
    ä»»æĢ§
    -0.25
     Adj
    -0.24
    åĪļåĪļ
    -0.24
    POSITIVE LOGITS
     drive
    0.27
    eenth
    0.27
     khóa
    0.27
    bugs
    0.26
    estic
    0.26
     depress
    0.26
    oons
    0.25
    ponsors
    0.25
     republic
    0.25
     drives
    0.25
    Activations Density 0.095%

    No Known Activations