© 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. 23769
    Prev
    Next
    INDEX
    Explanations

    training and skills

    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
     Nhi
    -0.28
    ductor
    -0.26
    еÑģÑĤ
    -0.25
     gracious
    -0.25
     wah
    -0.24
     Wu
    -0.24
     besch
    -0.24
    éĺ³
    -0.24
    .ev
    -0.24
     grac
    -0.24
    POSITIVE LOGITS
    apult
    0.31
    -selection
    0.26
    -degree
    0.26
    íıIJ
    0.26
    æĸ½å±ķ
    0.26
    uala
    0.25
    éĢīå®ļ
    0.25
     degree
    0.25
    æģĴ
    0.25
    ä¸ĵåĮº
    0.24
    Activations Density 0.000%

    No Known Activations