© 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. 97595
    Prev
    Next
    INDEX
    Explanations

    Code/Data identifiers

    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
    ãĢģ“
    -0.25
    sequ
    -0.25
    çļĦéĢļçŁ¥
    -0.25
     so
    -0.25
    ssize
    -0.24
     rem
    -0.24
     ind
    -0.24
     Freed
    -0.23
     B
    -0.23
    |↵
    -0.23
    POSITIVE LOGITS
     unleashed
    0.26
    æĢ¥
    0.26
    ourke
    0.26
    etically
    0.25
    .throw
    0.24
    ARIO
    0.24
    å¤ı
    0.24
    jection
    0.24
    失è°ĥ
    0.23
    оÑģÑĤÑĮÑİ
    0.23
    Activations Density 0.065%

    No Known Activations