© 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. 25-TRANSCODER-HP
    7. 108783
    Prev
    Next
    INDEX
    Explanations

    code punctuations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĢĤï¼Ī
    -0.42
    }}"↵
    -0.41
    ";č↵
    -0.40
    ";č↵č↵
    -0.40
    ;";↵
    -0.40
     ".";↵
    -0.40
    "č↵č↵
    -0.40
    ”↵↵
    -0.38
    .";č↵
    -0.37
    "]]↵
    -0.37
    POSITIVE LOGITS
    )↵
    0.60
    )
    0.59
     )
    0.59
    ):
    0.58
    ...)↵
    0.58
     )↵
    0.57
     )↵↵
    0.56
    ).↵
    0.54
     ...)
    0.54
    ).
    0.54
    Activations Density 1.090%

    No Known Activations