© 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. 129297
    Prev
    Next
    INDEX
    Explanations

    programming forum posts

    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
     lh
    -0.25
    ä¿Ĺ称
    -0.25
    &A
    -0.24
     lesbian
    -0.23
    .quant
    -0.23
     baptized
    -0.23
    TE
    -0.22
    èĦĶ
    -0.22
    Reporting
    -0.22
     gehört
    -0.22
    POSITIVE LOGITS
    agnar
    0.28
    çªľ
    0.26
    ogne
    0.24
    à´´
    0.24
    front
    0.24
    raith
    0.24
    ',['
    0.24
    è¿
    0.23
     MacDonald
    0.23
    渥
    0.23
    Activations Density 0.013%

    No Known Activations