© 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. 87593
    Prev
    Next
    INDEX
    Explanations

    English suffixes

    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
    OB
    -0.24
    æ³ķå¾ĭ顾éĹ®
    -0.24
     picturesque
    -0.24
    è¿ĺæĺ¯
    -0.23
    Invoker
    -0.23
    _BUSY
    -0.23
    Wind
    -0.23
    æİ¡åıĸ
    -0.23
    urv
    -0.23
     Wind
    -0.23
    POSITIVE LOGITS
    bury
    0.25
    éĢĢåĩº
    0.24
    çļĦ认åı¯
    0.23
    çļĦ大
    0.23
    çīĪæľ¬
    0.23
    odem
    0.23
    -away
    0.23
    ia
    0.23
    çļĦä¾ĭåŃIJ
    0.22
     cele
    0.22
    Activations Density 0.153%

    No Known Activations