© 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. 141903
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åŁŁ
    -0.26
     Glob
    -0.24
    ypress
    -0.24
    ãģªãģĦãĤĪãģĨãģ«
    -0.24
    credited
    -0.24
    earch
    -0.24
    å½ĵä¸ĭ
    -0.24
     FOUND
    -0.24
    еж
    -0.23
    æĬĢèĥ½
    -0.23
    POSITIVE LOGITS
    åĩĮ
    0.26
    ,var
    0.25
    åı±
    0.24
    -shaped
    0.24
    tips
    0.24
     scrambling
    0.24
     infinity
    0.23
    icity
    0.23
    jen
    0.23
    umbing
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.