© 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. 130438
    Prev
    Next
    INDEX
    Explanations

    names and dates, code

    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
    éĻIJ
    -0.29
    ä»ģ
    -0.27
     BITS
    -0.26
    ?):
    -0.26
    éĩį
    -0.25
    æł¹æľ¬
    -0.25
    chied
    -0.25
    ãģ£ãģ¦ãģįãģŁ
    -0.23
    æīĭæ³ķ
    -0.23
    æīĭèĩĤ
    -0.23
    POSITIVE LOGITS
     inertia
    0.29
     worth
    0.26
     corrid
    0.25
    èĽ¾
    0.24
    ifiable
    0.24
     state
    0.24
     friction
    0.24
    IDS
    0.24
     ide
    0.23
     rockets
    0.23
    Activations Density 0.002%

    No Known Activations