© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29284
    Prev
    Next
    INDEX
    Explanations

    represents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ronym
    -0.27
    esen
    -0.26
    ä¹Łæľīå¾Īå¤ļ
    -0.26
    å±Ĥå±Ĥ
    -0.25
     bit
    -0.25
    pline
    -0.25
    adian
    -0.24
     grow
    -0.24
     AM
    -0.24
     terse
    -0.24
    POSITIVE LOGITS
    ÑĤив
    0.29
    Playback
    0.28
    imenti
    0.27
    ims
    0.27
    æĺ¯æ¯Ķè¾ĥ
    0.27
    ivating
    0.26
    audio
    0.26
    æī¿
    0.26
    ÙħÙĨظÙħ
    0.25
    clock
    0.24
    Activations Density 0.590%

    No Known Activations