© 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. 8492
    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
     recover
    -0.26
    è¿ĩåħ³
    -0.25
    åıĸåĨ³
    -0.25
     lick
    -0.24
    esper
    -0.24
    omore
    -0.24
    æĤ¬å´ĸ
    -0.24
    notes
    -0.23
     antid
    -0.23
    recover
    -0.23
    POSITIVE LOGITS
    indle
    0.29
     vol
    0.28
    åĵģ
    0.27
    æĺ¯ä¸ĢåIJį
    0.26
     phẩm
    0.26
    -choice
    0.26
    yle
    0.26
    icide
    0.26
     standard
    0.25
    ноÑģÑĤÑĮ
    0.25
    Activations Density 0.039%

    No Known Activations

    This feature has no known activations.