© 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. 129803
    Prev
    Next
    INDEX
    Explanations

    Instructions, requirements, applications

    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
    iej
    -0.28
     Depos
    -0.27
    èĮ¶åĽŃ
    -0.26
     souvent
    -0.25
    说èĩªå·±
    -0.25
     instincts
    -0.25
    often
    -0.25
    ulous
    -0.25
    çİ©æĦı
    -0.25
    åij³
    -0.24
    POSITIVE LOGITS
     submission
    0.47
     submitting
    0.43
     submit
    0.40
     submitted
    0.39
    .Submit
    0.38
     MUST
    0.38
    æıIJ交
    0.37
     Submit
    0.37
    submit
    0.36
    ä¸įå¾Ĺ
    0.35
    Activations Density 0.019%

    No Known Activations