© 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. 112538
    Prev
    Next
    INDEX
    Explanations

    Text extraction with names

    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
    -ish
    -0.30
    XL
    -0.29
    ãĥ¼ãĤ·
    -0.26
     ton
    -0.26
    ä¸Ģä¸Ŀ
    -0.25
    æľĢåIJİä¸Ģ次
    -0.25
    inyin
    -0.25
    è¿ĩ
    -0.25
    è¿ĩå¹´
    -0.25
    ubes
    -0.25
    POSITIVE LOGITS
    mites
    0.26
    CKER
    0.26
     Bracket
    0.25
    irable
    0.25
    Bracket
    0.24
     newPos
    0.24
    ments
    0.24
    éºĴ
    0.24
     Channels
    0.24
    ç¬ŀ
    0.23
    Activations Density 0.001%

    No Known Activations