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. 46439
    Prev
    Next
    INDEX
    Explanations

    cep

    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
    ãĤ¿ãĥ¼
    -0.28
    lık
    -0.26
     claw
    -0.26
    eful
    -0.25
     tá»ij
    -0.24
     compar
    -0.24
    _TRANSACTION
    -0.24
     learner
    -0.24
    ocolate
    -0.23
    æ°´éĿ¢
    -0.23
    POSITIVE LOGITS
    以å¤ĸ
    0.34
    bots
    0.26
    è§ģ
    0.26
    空
    0.26
    utow
    0.26
    ä¹ĭå¤ĸ
    0.25
    èĿ¼
    0.25
    è¿
    0.25
    å°±åºĶ该
    0.25
    å¥Ĺ
    0.25
    Activations Density 0.324%

    No Known Activations