© 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. 12-TRANSCODER-HP
    7. 23244
    Prev
    Next
    INDEX
    Explanations

    rural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıijå¸ĥæŶéĹ´
    -0.43
    没äºĨ
    -0.27
    éĴ±å¸ģ
    -0.26
     stripper
    -0.25
    æł·
    -0.25
    éªĮè¯ģçłģ
    -0.24
    åĮ¹éħį
    -0.24
    æĺ¨æĹ¥
    -0.24
    çļĦæĺ¯
    -0.23
    ä¸ĢæŦ
    -0.23
    POSITIVE LOGITS
    sat
    0.28
    SAT
    0.28
    DAQ
    0.27
    alto
    0.27
    ml
    0.27
    sov
    0.26
    è¾ľ
    0.25
     sadd
    0.25
     altogether
    0.24
     ml
    0.24
    Activations Density 0.003%

    No Known Activations