© 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. 87978
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    rente
    -0.28
    GetX
    -0.28
     Bust
    -0.27
    niest
    -0.27
     drowning
    -0.26
    çİ°éĩijæµģ
    -0.26
    ê·Ģ
    -0.26
    èĭģ
    -0.26
    éĽĨä¸Ń
    -0.25
    è¿ĩç¨ĭå½ĵä¸Ń
    -0.25
    POSITIVE LOGITS
    ç»Ħç»ĩ
    0.28
    å±ŀ
    0.26
    ä½ľä¸ļ
    0.25
     Loc
    0.24
    åŃ¢
    0.24
    å°ıåŀĭ
    0.23
    (Sub
    0.23
    .Abstract
    0.23
    èĥĮåĮħ
    0.23
    设å¤ĩ
    0.23
    Activations Density 0.007%

    No Known Activations