© 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. 23400
    Prev
    Next
    INDEX
    Explanations

    Names, code, formal communication

    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
    åİĭåĬĽ
    -0.27
    çļĦåİĭåĬĽ
    -0.26
     corre
    -0.26
    extrême
    -0.25
    alty
    -0.25
    æĦıè§ģ建议
    -0.25
    åĢĴæĺ¯
    -0.25
    å¸ĪåħĦ
    -0.24
    æµ·è¿IJ
    -0.24
    ä¹Ĺ
    -0.24
    POSITIVE LOGITS
    werk
    0.31
    èĬ
    0.29
    opies
    0.28
    yh
    0.27
    åĤ»
    0.27
     sense
    0.26
     bund
    0.26
    idth
    0.26
    :hidden
    0.26
    带
    0.26
    Activations Density 0.001%

    No Known Activations