© 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. 20-TRANSCODER-HP
    7. 64422
    Prev
    Next
    INDEX
    Explanations

    school grades

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĿĢäºĨ
    -0.28
     Kills
    -0.26
    çĻ½èī²çļĦ
    -0.26
    	RTE
    -0.25
    çĽĴåŃIJ
    -0.25
    ëŀľ
    -0.25
    -mouth
    -0.25
     parallels
    -0.24
    LAND
    -0.24
    lights
    -0.24
    POSITIVE LOGITS
    æĩĤ
    0.30
     underst
    0.28
    ä¼ł
    0.25
    驹
    0.25
    侧éĩį
    0.25
    tabl
    0.24
    اسÙĬ
    0.24
    omez
    0.24
    eries
    0.23
     diagnostics
    0.23
    Activations Density 0.780%

    No Known Activations