© 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. 111984
    Prev
    Next
    INDEX
    Explanations

    Descriptions and biographies

    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
    side
    -0.27
    åĩij
    -0.24
     enter
    -0.24
    íķĻêµIJ
    -0.23
    Invest
    -0.23
    æ¢ł
    -0.23
     Herc
    -0.23
    	e
    -0.23
    egg
    -0.23
     side
    -0.23
    POSITIVE LOGITS
    %p
    0.29
    åī§æľ¬
    0.25
    TERN
    0.25
    pard
    0.24
    é¢ijç¹ģ
    0.24
    adel
    0.24
    iples
    0.24
    ifr
    0.24
    ambique
    0.23
    Ä±ÅŁ
    0.23
    Activations Density 0.153%

    No Known Activations