© 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. 22-TRANSCODER-HP
    7. 98473
    Prev
    Next
    INDEX
    Explanations

    Various grammatically correct texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įä¼ļ
    -0.52
    没æľī
    -0.50
    ä¸įä¼ļæľī
    -0.49
    ä¸įèĥ½
    -0.48
    ä¸įåģļ
    -0.47
    ä¸įéľĢè¦ģ
    -0.47
    并没æľī
    -0.46
    ä¸įåĨį
    -0.46
    ä¸įå¿ħ
    -0.46
    没æľīä»»ä½ķ
    -0.45
    POSITIVE LOGITS
    enames
    0.30
    æľīæĿ¡ä»¶
    0.30
    æ¯ı次éĥ½
    0.27
    empre
    0.25
    arella
    0.24
    thing
    0.24
    iek
    0.23
    >}
    0.23
    endo
    0.23
    ".$_
    0.22
    Activations Density 0.008%

    No Known Activations