© 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. 112340
    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
    //{{
    -0.30
    <?↵
    -0.30
    åĢĻéĢī
    -0.29
    åĹħ
    -0.27
    æ¿ij
    -0.27
    åĽł
    -0.26
    è¾ŀ
    -0.25
    åį«çĶŁéĹ´
    -0.25
    çĶļ
    -0.24
    ÑĢем
    -0.23
    POSITIVE LOGITS
    让å®ĥ
    0.29
    cene
    0.28
    ham
    0.26
    ëĭ´
    0.25
    imate
    0.25
    èĩ¾
    0.25
    лага
    0.24
    _SOL
    0.24
    istrator
    0.24
    alted
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.