© 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. 87685
    Prev
    Next
    INDEX
    Explanations

    health improvement

    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
     McCl
    -0.30
    ucch
    -0.28
    iado
    -0.28
    çļĦæĪIJåĬŁ
    -0.26
    å±ĭ
    -0.26
    è¿ĩåī©
    -0.26
    顺åĪ©
    -0.25
    POSITE
    -0.25
    uai
    -0.24
    ué
    -0.24
    POSITIVE LOGITS
     discriminate
    0.27
    ese
    0.26
     daytime
    0.26
    éĴ»çŁ³
    0.26
    fte
    0.25
    -front
    0.24
    /front
    0.24
    .lines
    0.24
     cere
    0.24
     front
    0.24
    Activations Density 0.003%

    No Known Activations