© 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. 112433
    Prev
    Next
    INDEX
    Explanations

    disagreement

    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
    .exports
    -0.25
    æĮĤåľ¨
    -0.24
    çĬ¶åĨµ
    -0.24
    transpose
    -0.23
    Typed
    -0.23
    rsa
    -0.23
    åĵĶ
    -0.23
    conditions
    -0.23
     dass
    -0.22
    å¿«æĬ¥
    -0.22
    POSITIVE LOGITS
     anecd
    0.34
    ading
    0.29
    ingly
    0.29
    erne
    0.26
    liest
    0.26
     analogy
    0.26
     argument
    0.26
    uish
    0.25
    XL
    0.25
    arguments
    0.25
    Activations Density 0.009%

    No Known Activations