© 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. 111570
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
     integrated
    -0.30
     refinement
    -0.30
     refined
    -0.29
    6
    -0.28
     strategy
    -0.27
    rm
    -0.26
     Integrated
    -0.26
     McM
    -0.25
     prefixed
    -0.25
    Mc
    -0.25
    POSITIVE LOGITS
    lut
    0.28
     Amp
    0.28
    ROTO
    0.28
    æĴŀ
    0.28
    flate
    0.27
     bais
    0.26
    aldi
    0.25
    绦
    0.25
    ierz
    0.25
     báºŃt
    0.25
    Activations Density 0.009%

    No Known Activations