© 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. 112092
    Prev
    Next
    INDEX
    Explanations

    adverbs

    np_max-act · gemini-2.0-flash
    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
    ä»İä¸Ń
    -0.27
    )init
    -0.26
    orderid
    -0.25
    inem
    -0.25
     relative
    -0.25
    -relative
    -0.25
     unw
    -0.24
     cause
    -0.24
     exhibit
    -0.24
    oldt
    -0.24
    POSITIVE LOGITS
    人寿
    0.28
     дан
    0.25
    çĽ²
    0.25
    _nf
    0.25
    空
    0.25
    èĨı
    0.24
    æ´²
    0.24
    éģ¥
    0.24
    chts
    0.24
    èµ°è¿Ľ
    0.24
    Activations Density 0.048%

    No Known Activations