© 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. 33-TRANSCODER-HP
    7. 53604
    Prev
    Next
    INDEX
    Explanations

    seven

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    9
    -0.53
    ï¼Ļ
    -0.46
    ä¹Ŀ
    -0.44
     Nine
    -0.40
     nine
    -0.40
     ninety
    -0.38
    -nine
    -0.36
    ଽ
    -0.34
     дев
    -0.33
    nine
    -0.32
    POSITIVE LOGITS
     seven
    0.32
    ä¸ĥ个
    0.32
    seven
    0.30
     seventeen
    0.29
     seventh
    0.28
    ä¸ĥ
    0.28
    ä¸ĥå¹´
    0.28
    åįģä¸ĥæĿ¡
    0.28
    indow
    0.26
     sevent
    0.26
    Activations Density 0.007%

    No Known Activations