© 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. 98971
    Prev
    Next
    INDEX
    Explanations

    hyphens

    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
    顶å±Ĥ
    -0.26
    ADX
    -0.26
    opoulos
    -0.25
    AppState
    -0.25
    ORN
    -0.24
    èį¦
    -0.24
    lijk
    -0.24
    isque
    -0.24
    个å°ı
    -0.24
    marvin
    -0.23
    POSITIVE LOGITS
     RADIO
    0.24
    quip
    0.24
    gal
    0.24
    </
    0.24
     wifi
    0.24
    غÙĨÙĬ
    0.24
     </>↵
    0.24
     WiFi
    0.24
    /english
    0.24
     cigaret
    0.23
    Activations Density 0.004%

    No Known Activations