© 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. 23549
    Prev
    Next
    INDEX
    Explanations

    7

    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
     strokes
    -0.28
    postId
    -0.25
    oks
    -0.24
    æİĴ
    -0.24
     nxt
    -0.24
    ">#
    -0.24
    gaben
    -0.24
    nP
    -0.23
    	post
    -0.23
     post
    -0.23
    POSITIVE LOGITS
    completion
    0.30
    Łèĥ½
    0.25
    rength
    0.25
    .border
    0.25
    åı«
    0.25
    uada
    0.24
    çľ
    0.24
    ä»£è¡¨åĽ¢
    0.24
     reflecting
    0.24
    Mutable
    0.24
    Activations Density 0.006%

    No Known Activations