© 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. 87610
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     Says
    -0.31
     ret
    -0.26
    ç¬ijçĿĢ说
    -0.25
    ”;
    -0.25
    åĨħå¿ĥçļĦ
    -0.24
     mutual
    -0.24
    æīĭä¸ŃçļĦ
    -0.24
    says
    -0.23
     Ret
    -0.23
     Said
    -0.23
    POSITIVE LOGITS
    çĥ¦
    0.27
    åĩij
    0.27
    pike
    0.26
    ãģĬé¡ĺãģĦ
    0.26
    æĶ¶æķĽ
    0.24
    Ñīи
    0.24
     suck
    0.24
    alis
    0.24
    ÑĥÑĩ
    0.24
     Fist
    0.23
    Activations Density 0.010%

    No Known Activations