© 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. 130375
    Prev
    Next
    INDEX
    Explanations

    axis

    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
    æķĻä½ł
    -0.27
    ÑĩиÑģÑĤ
    -0.27
    å¿ł
    -0.27
    ç»´å¥ĩ
    -0.26
     Bacon
    -0.25
    令
    -0.25
    avourite
    -0.25
    CAF
    -0.24
    æ®ĥ
    -0.23
    uest
    -0.23
    POSITIVE LOGITS
    å¾·æĭī
    0.29
    æ¡Ĩ
    0.26
    ÙĪÙħ
    0.26
    haar
    0.25
    åĨķ
    0.25
    umu
    0.25
    icular
    0.24
    è£Ł
    0.24
    é«ģ
    0.24
    jd
    0.24
    Activations Density 0.130%

    No Known Activations