© 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. 97979
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    åĴĮåħ¶ä»ĸ
    -0.33
    cat
    -0.28
    à¹ģà¸Ķà¸ĩ
    -0.27
    æݨä»ĭ
    -0.26
     cat
    -0.26
    매
    -0.26
    åı¯èĥ½åĩºçİ°
    -0.25
    æī¾ä¸ª
    -0.24
    füg
    -0.24
    åıĬåħ¶ä»ĸ
    -0.24
    POSITIVE LOGITS
     `_
    0.29
     '*',
    0.26
     (!_
    0.25
    >(_
    0.25
    uten
    0.24
    è··
    0.24
    ohon
    0.23
    ÑĥлÑĮÑĤ
    0.23
    åĩ¡æľ¬ç½ij
    0.23
    ylum
    0.22
    Activations Density 0.024%

    No Known Activations