© 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. 23643
    Prev
    Next
    INDEX
    Explanations

    web pages, code

    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
     waters
    -0.29
    éķ«
    -0.28
    moment
    -0.28
    èįŀ
    -0.27
    ails
    -0.25
    æ°´èµĦæºIJ
    -0.25
    _attachment
    -0.25
    wing
    -0.25
    鸨
    -0.25
    å¼ĤæĢ§
    -0.24
    POSITIVE LOGITS
    åıįèħIJ
    0.27
    icolor
    0.25
    EditingController
    0.25
    ä¸įè¦ģ太
    0.23
    él
    0.23
    zeich
    0.23
    azu
    0.23
     Specs
    0.23
    ä¸įå¾Ĺ
    0.23
    fä
    0.23
    Activations Density 0.000%

    No Known Activations