© 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. 112691
    Prev
    Next
    INDEX
    Explanations

    Paris

    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
    ivery
    -0.29
    xAA
    -0.29
     scenery
    -0.27
    elight
    -0.27
     "#"
    -0.27
    çŧ
    -0.26
     minimalist
    -0.26
     belts
    -0.26
    iÃŁ
    -0.25
    lights
    -0.25
    POSITIVE LOGITS
     Burk
    0.27
    pos
    0.25
    (cors
    0.25
    èħĬ
    0.24
    esar
    0.24
    Track
    0.24
    çݯå¢ĥä¿ĿæĬ¤
    0.24
    pn
    0.23
     Track
    0.23
    è´¿
    0.23
    Activations Density 0.020%

    No Known Activations