© 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. 129738
    Prev
    Next
    INDEX
    Explanations

    scientific publications

    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
    å¥ijæľº
    -0.27
    cesso
    -0.27
     exit
    -0.27
    handleRequest
    -0.26
    åĪĨæīĭ
    -0.25
    人æµģ
    -0.25
    OLON
    -0.25
    omination
    -0.25
    æľºæ²¹
    -0.25
    ará
    -0.24
    POSITIVE LOGITS
     elemental
    0.24
    Transient
    0.24
    ä¸įå®Į
    0.24
    elli
    0.23
    trinsic
    0.23
     Fer
    0.23
    Reserved
    0.23
     Teddy
    0.23
    our
    0.22
     Phi
    0.22
    Activations Density 0.004%

    No Known Activations