© 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. 111440
    Prev
    Next
    INDEX
    Explanations

    Pasta

    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
    gable
    -0.32
    er
    -0.31
    ä½ĵåĬĽ
    -0.29
    onom
    -0.28
    i
    -0.27
    Ren
    -0.26
    tons
    -0.26
    able
    -0.25
    de
    -0.25
    set
    -0.25
    POSITIVE LOGITS
    jong
    0.28
    TING
    0.28
     understandably
    0.27
     supper
    0.27
    tring
    0.26
     Cors
    0.25
     |_|
    0.25
     populations
    0.24
     electorate
    0.24
    -election
    0.24
    Activations Density 0.041%

    No Known Activations