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. 27-TRANSCODER-HP
    4. 850
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anie
    -0.26
    izable
    -0.26
    GF
    -0.26
    gf
    -0.25
     cumulative
    -0.25
    çŃł
    -0.25
    ูล
    -0.24
    cum
    -0.24
    olare
    -0.24
    cp
    -0.24
    POSITIVE LOGITS
    èIJ½
    0.30
    ä¼ļè®®
    0.27
    EV
    0.27
    管çIJĨåĬŀæ³ķ
    0.26
    shall
    0.24
    æľī害
    0.24
    åħ¨ä½ĵåijĺå·¥
    0.24
    èIJ½åΰ
    0.24
    æľĥèѰ
    0.23
    为ä¸Ńå¿ĥ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.