© 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. 98453
    Prev
    Next
    INDEX
    Explanations

    Random excerpts

    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
     вÑģÑı
    -0.27
    аÑı
    -0.26
    UBE
    -0.25
    -described
    -0.25
    åģı
    -0.24
    æIJľ
    -0.24
     foreseeable
    -0.24
    anda
    -0.23
    ÂŃtion
    -0.23
     leaked
    -0.23
    POSITIVE LOGITS
    bite
    0.30
    utivo
    0.26
    olib
    0.25
    好人
    0.25
    hé
    0.24
    æ³ķåĪ¶
    0.24
    çݰ代
    0.24
    çı¾ä»£
    0.24
    æĹłæīĢè°ĵ
    0.24
    uctor
    0.23
    Activations Density 0.002%

    No Known Activations