© 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. 129989
    Prev
    Next
    INDEX
    Explanations

    Part

    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
    é£İåIJ¹
    -0.28
    æīĭæĦŁ
    -0.27
    æĽ´ä½ķåĨµ
    -0.26
     hindsight
    -0.25
    åĩłæŃ¥
    -0.24
     Wh
    -0.24
     sympathy
    -0.23
     Lie
    -0.23
     Stat
    -0.23
    çĶŁç´ł
    -0.23
    POSITIVE LOGITS
     listings
    0.25
    PRESENT
    0.25
    oro
    0.24
     présente
    0.23
    verbs
    0.23
    å±ŀæĢ§
    0.23
    .twig
    0.23
    æľīçļĦ
    0.23
    istrate
    0.23
    CMS
    0.23
    Activations Density 0.409%

    No Known Activations