© 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. 57954
    Prev
    Next
    INDEX
    Explanations

    email headers

    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
     communication
    -0.93
    æ²ŁéĢļ
    -0.87
    communication
    -0.79
     communicates
    -0.79
     Communication
    -0.79
     communicate
    -0.79
    Communication
    -0.76
     communicating
    -0.75
    éĢļä¿¡
    -0.75
    éĢļ讯
    -0.72
    POSITIVE LOGITS
    erald
    0.29
     tern
    0.26
    ber
    0.26
     Seasons
    0.25
    tur
    0.25
    zu
    0.24
    azzo
    0.24
    åı¥
    0.23
    Cb
    0.23
    åıłåĬł
    0.23
    Activations Density 0.001%

    No Known Activations