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. 146461
    Prev
    Next
    INDEX
    Explanations

    technical and online content

    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
    ä¸ĩ象
    -0.29
    -ref
    -0.28
    峪
    -0.27
    unami
    -0.26
     jams
    -0.26
    -Allow
    -0.25
    ToPoint
    -0.25
    -par
    -0.25
     recall
    -0.25
    CDATA
    -0.25
    POSITIVE LOGITS
    erta
    0.27
    illas
    0.24
    éĤ£ç§į
    0.24
    erged
    0.24
    ÑģÑĤи
    0.23
    enery
    0.23
    å¸ĥæľĹ
    0.23
    ONS
    0.23
     Asked
    0.23
     amo
    0.23
    Activations Density 0.026%

    No Known Activations