© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 56863
    Prev
    Next
    INDEX
    Explanations

    Subjective qualities

    np_max-act-logits · gemini-2.0-flash
    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
    çļĦå°±æĺ¯
    -0.31
     spot
    -0.30
    =""><
    -0.28
    ="#"><
    -0.28
    umpt
    -0.28
    éĥ½ä¼ļæľī
    -0.28
     Isles
    -0.27
    esub
    -0.26
    pageNumber
    -0.26
    å¥ĩçī¹
    -0.26
    POSITIVE LOGITS
    ingly
    0.27
    JI
    0.25
     similarly
    0.24
    åľ¨çİ°åľº
    0.24
    ellow
    0.24
    inally
    0.24
    éĨī
    0.24
    ł
    0.24
    arily
    0.24
     gle
    0.24
    Activations Density 0.790%

    No Known Activations