© 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. 130489
    Prev
    Next
    INDEX
    Explanations

    describing_large_extent

    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
    igo
    -0.26
    (&(
    -0.24
    çķ¶æĤ¨
    -0.24
     every
    -0.23
    irs
    -0.23
    Ó£
    -0.23
    éĺ³
    -0.23
     während
    -0.22
    åł¤
    -0.22
    amble
    -0.22
    POSITIVE LOGITS
    igated
    0.31
    perc
    0.30
    IPH
    0.27
    ä¸ĢåĪ»
    0.26
    sert
    0.26
    nı
    0.26
    严éĩįçļĦ
    0.25
    èµĦ
    0.25
    å¾Īå·®
    0.25
    å¾Īé«ĺçļĦ
    0.25
    Activations Density 0.014%

    No Known Activations