© 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. 97868
    Prev
    Next
    INDEX
    Explanations

    champion

    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
    ipher
    -0.29
    ancement
    -0.28
    ä¸īåĪĨ
    -0.26
    oley
    -0.25
    urement
    -0.25
     Hir
    -0.25
    ADF
    -0.25
    éļ¶
    -0.24
    ako
    -0.24
    é¢Ľ
    -0.24
    POSITIVE LOGITS
    icide
    0.28
     settings
    0.27
    /Linux
    0.26
     later
    0.26
     uns
    0.25
    å¾Ĥ
    0.24
     undert
    0.24
     unders
    0.24
     surre
    0.24
    ToArray
    0.24
    Activations Density 0.026%

    No Known Activations