© 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. 22-TRANSCODER-HP
    7. 112327
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <decltype
    -0.26
    ión
    -0.26
    iminal
    -0.26
    ebin
    -0.25
    è¯į
    -0.23
     taboo
    -0.23
    ibal
    -0.23
     sint
    -0.23
    -indent
    -0.22
    idel
    -0.22
    POSITIVE LOGITS
    æĦŁæ¿Ģ
    0.28
    太é«ĺ
    0.27
     needle
    0.25
    eus
    0.24
    hausen
    0.24
    ç¿ħèĨĢ
    0.24
    utra
    0.24
    species
    0.24
    etus
    0.24
     hơi
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.