© 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. 112686
    Prev
    Next
    INDEX
    Explanations

    helping

    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
    hevik
    -0.28
    essor
    -0.27
    (cljs
    -0.25
    á»Ŀ
    -0.25
     electr
    -0.24
    stdClass
    -0.24
     Eyl
    -0.24
    enko
    -0.24
    chestra
    -0.24
    çĶµè´¹
    -0.24
    POSITIVE LOGITS
    paring
    0.25
     Aspect
    0.24
    -times
    0.23
     Laugh
    0.23
     Shall
    0.23
    -am
    0.23
    娣
    0.23
     Morning
    0.23
     Smooth
    0.23
     specialist
    0.23
    Activations Density 0.026%

    No Known Activations