© 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. 63039
    Prev
    Next
    INDEX
    Explanations

    negations

    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
    æĪ³
    -0.30
     pretended
    -0.30
    encion
    -0.28
    缮çļĦ
    -0.27
    .native
    -0.27
    è§īéĨĴ
    -0.26
    cribe
    -0.26
    åıijçİ°èĩªå·±
    -0.25
    说çļĦæĺ¯
    -0.25
    kel
    -0.25
    POSITIVE LOGITS
    ä¸Ľä¹¦
    0.31
    åħ¼é¡¾
    0.31
    éĢĤ度
    0.25
    éĢĤæŶ
    0.25
    educ
    0.25
    owel
    0.25
    æı©
    0.25
    estring
    0.24
    .ent
    0.24
    çİ©ç¬ij
    0.24
    Activations Density 13.572%

    No Known Activations