© 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. 22750
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
     operator
    -0.28
    operator
    -0.27
    AGES
    -0.26
     rt
    -0.25
    æľªèĥ½
    -0.25
    age
    -0.25
     kÃŃnh
    -0.24
    æĮĸæİĺ
    -0.23
     rv
    -0.23
    Conversion
    -0.23
    POSITIVE LOGITS
    ablish
    0.27
    ç¾İåĽ½äºº
    0.27
    [ch
    0.26
     ado
    0.26
    æĶ¾å¿ĥ
    0.26
    tÃŃ
    0.26
    imated
    0.25
    ело
    0.25
    oded
    0.24
    iscal
    0.24
    Activations Density 0.011%

    No Known Activations