© 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. 64229
    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
    TextInput
    -0.26
    æĹłæķ°æ¬¡
    -0.26
    çļĦåIJĪä½ľ
    -0.25
    lbrace
    -0.24
    ä¾£
    -0.24
    .Handled
    -0.24
    æľīæľŁ
    -0.24
    nit
    -0.24
    lst
    -0.24
     crusher
    -0.24
    POSITIVE LOGITS
    éģĹ
    0.31
     classical
    0.28
     attributable
    0.27
    RES
    0.25
    éķ¿éķ¿çļĦ
    0.25
    çĭ¬
    0.25
     sophistic
    0.24
    Vs
    0.24
    ç«ŁçĦ¶
    0.24
     indigenous
    0.24
    Activations Density 2.884%

    No Known Activations

    This feature has no known activations.