© 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. 98262
    Prev
    Next
    INDEX
    Explanations

    Contractions

    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
    æĪij们ä¼ļ
    -0.34
    ä¸Ģå¾ĭ
    -0.27
    æľīåĪ©
    -0.26
    该åİ¿
    -0.26
    rarian
    -0.25
    è¯¥é¡¹çĽ®
    -0.25
    æľīçĽĬ
    -0.24
    -we
    -0.24
    æĪij们
    -0.24
     Koch
    -0.23
    POSITIVE LOGITS
     Criterion
    0.26
    oli
    0.26
    ujet
    0.25
    née
    0.25
    åľ°çĭ±
    0.25
     trì
    0.24
    çĭ¬
    0.24
    Chance
    0.24
    ffff
    0.24
    éĴĽ
    0.24
    Activations Density 0.004%

    No Known Activations