© 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. 129691
    Prev
    Next
    INDEX
    Explanations

    code

    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
    alse
    -0.27
    æĮģèĤ¡
    -0.27
     though
    -0.26
    ivities
    -0.26
     gyr
    -0.24
    æŀ¶
    -0.24
    _owned
    -0.24
     erm
    -0.24
    inals
    -0.24
    åĪĿå§ĭ
    -0.23
    POSITIVE LOGITS
    Fo
    0.28
    éļıå¤Ħ
    0.27
    !*
    0.26
    wallet
    0.25
    h
    0.24
    é¢ī
    0.24
    aku
    0.24
    req
    0.24
    Ao
    0.24
    æīĭå·¥
    0.24
    Activations Density 0.005%

    No Known Activations