© 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. 19-TRANSCODER-HP
    7. 7781
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hit
    -0.26
    缺åı£
    -0.26
     rescue
    -0.25
    -g
    -0.24
     unidentified
    -0.24
    alloca
    -0.24
     receptions
    -0.24
    opia
    -0.23
    baugh
    -0.23
    enabled
    -0.23
    POSITIVE LOGITS
    idor
    0.28
     ffi
    0.26
    ï½ŀ↵↵
    0.26
    subs
    0.25
    (':
    0.24
    åŃļ
    0.23
    伺
    0.23
     ëį
    0.23
     Translate
    0.23
    é¢IJ
    0.23
    Activations Density 1.701%

    No Known Activations

    This feature has no known activations.