© 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. 112077
    Prev
    Next
    INDEX
    Explanations

    Cam

    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
    æĪijå¾Ī
    -0.27
    ç®±
    -0.26
    myp
    -0.26
    ert
    -0.25
    erta
    -0.25
    å¾ģ
    -0.25
    æĸ©
    -0.25
    enic
    -0.24
     flats
    -0.24
    äºİä¸Ģä½ĵ
    -0.24
    POSITIVE LOGITS
     Prev
    0.29
    prev
    0.26
     prev
    0.25
    )arg
    0.25
     {?
    0.25
     dÃły
    0.25
     ëĵ±ìĿĺ
    0.24
    ......
    0.24
     Modi
    0.24
    ivan
    0.24
    Activations Density 0.016%

    No Known Activations