© 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. 88449
    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
     Ridley
    -0.28
    æĦıè§ģåıįé¦Ī
    -0.26
    TRS
    -0.23
     YT
    -0.23
    åĵģç§į
    -0.23
    YT
    -0.23
     Ingram
    -0.23
     floated
    -0.23
    éĻį
    -0.23
    NEG
    -0.23
    POSITIVE LOGITS
    uzz
    0.28
    ug
    0.27
    è½°
    0.26
    åİŁæĿIJæĸĻ
    0.25
    £¼
    0.24
    etsk
    0.24
    onym
    0.23
    Clinical
    0.23
     AUD
    0.22
     offsetof
    0.22
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.