© 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. 107469
    Prev
    Next
    INDEX
    Explanations

    ock

    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
    Sie
    -0.25
    Sur
    -0.24
    æĺ¨
    -0.24
    QRST
    -0.24
    [arr
    -0.24
     Sur
    -0.24
     CAR
    -0.23
    _sur
    -0.23
    éĻ£
    -0.23
    CAR
    -0.23
    POSITIVE LOGITS
    edly
    0.33
    ublished
    0.27
    fully
    0.27
    advertisement
    0.27
    verage
    0.25
     ad
    0.25
    _literals
    0.24
    æĿ·
    0.24
     bibliography
    0.24
     lateral
    0.23
    Activations Density 0.065%

    No Known Activations