© 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. 88118
    Prev
    Next
    INDEX
    Explanations

    own

    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
     doomed
    -0.28
    nonce
    -0.26
     artic
    -0.24
    ä¸ĢæīĢ
    -0.24
    oldown
    -0.24
    -secondary
    -0.24
     sevent
    -0.23
    (sender
    -0.23
    Nonce
    -0.23
     postseason
    -0.23
    POSITIVE LOGITS
    èĩªå·±çļĦ
    0.28
    äºĨèĩªå·±çļĦ
    0.28
    æŶä¸į
    0.27
    å°Ĩèĩªå·±çļĦ
    0.27
    伺
    0.27
    ä¸į解
    0.26
    èĩªå®¶
    0.26
    ç¨ĭå¼ı
    0.26
    orsi
    0.24
    è§Ĩ
    0.24
    Activations Density 0.015%

    No Known Activations