© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 129010
    Prev
    Next
    INDEX
    Explanations

    ent

    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
    Negative Logits
    ting
    -0.58
    ted
    -0.46
    ainment
    -0.39
    uning
    -0.36
    tle
    -0.35
    ively
    -0.35
    TING
    -0.34
    aylor
    -0.33
    aneous
    -0.33
    ypes
    -0.32
    POSITIVE LOGITS
    hdr
    0.30
    etta
    0.28
    venue
    0.27
    ster
    0.26
    ITY
    0.26
    hist
    0.25
    rats
    0.25
    hour
    0.25
    addy
    0.24
    etti
    0.24
    Activations Density 0.875%

    No Known Activations