© 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. 130499
    Prev
    Next
    INDEX
    Explanations

    Mixed internet text

    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
     interior
    -0.29
     hindsight
    -0.26
    ationally
    -0.26
     tuned
    -0.25
    ãģ¡ãģ¯
    -0.25
     garg
    -0.25
    ció
    -0.25
    çľĭä¸Ģçľĭ
    -0.24
     uncon
    -0.24
    .beginTransaction
    -0.24
    POSITIVE LOGITS
    ãģĿãģĨãģ§
    0.29
    éĽĨåĽ¢æĹĹä¸ĭ
    0.28
    pos
    0.25
     oder
    0.25
    å£ĵåĬĽ
    0.25
    å¦Ī
    0.25
    è¿ŀ
    0.25
    =====
    0.25
    inz
    0.24
    åIJ¦åĪĻ
    0.24
    Activations Density 0.001%

    No Known Activations