© 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. 87221
    Prev
    Next
    INDEX
    Explanations

    alternate

    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
    off
    -0.28
    Off
    -0.28
    aign
    -0.27
    ty
    -0.27
    mis
    -0.26
    æ¢Ń
    -0.26
    _Off
    -0.26
    sert
    -0.26
    Actually
    -0.26
    wald
    -0.26
    POSITIVE LOGITS
     versions
    0.31
     outputs
    0.30
     sources
    0.26
    çļĦå°ı
    0.26
     approaches
    0.25
     branches
    0.24
    /native
    0.24
     plans
    0.24
     methods
    0.24
     mega
    0.24
    Activations Density 0.024%

    No Known Activations