© 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. 130533
    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
    ISON
    -0.27
    ison
    -0.26
    ainment
    -0.26
     eBooks
    -0.25
     penet
    -0.25
    *R
    -0.25
    æĬ¥éĢģ
    -0.25
    éľīç´ł
    -0.25
     antis
    -0.24
    -black
    -0.24
    POSITIVE LOGITS
     NotImplemented
    0.29
     bet
    0.28
    åįł
    0.25
    æī¹æ¬¡
    0.25
    TURE
    0.25
     BET
    0.25
    äºĴ
    0.24
     seed
    0.24
    routine
    0.23
     pulumi
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.