© 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. 12-TRANSCODER-HP
    7. 22948
    Prev
    Next
    INDEX
    Explanations

    overhead

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĢĽ
    -0.26
    éĿĴæĺ¥
    -0.26
    åĽ¾çº¸
    -0.25
     веÑĩ
    -0.24
    ç¥ķ
    -0.24
     wizard
    -0.24
    -quarter
    -0.24
    imators
    -0.24
     Sheet
    -0.24
    lector
    -0.23
    POSITIVE LOGITS
    好äºĨ
    0.29
    æī¹
    0.28
    è¶Ĭ好
    0.28
    æĹłè®ºå¦Ĥä½ķ
    0.28
    æīģ
    0.28
     rez
    0.27
    tran
    0.27
     offer
    0.27
     prot
    0.26
     ident
    0.26
    Activations Density 0.048%

    No Known Activations