© 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. 130701
    Prev
    Next
    INDEX
    Explanations

    period

    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
    .gdx
    -0.25
     concerning
    -0.24
    è·ijæŃ¥
    -0.23
    riz
    -0.23
     ê´Ģíķľ
    -0.22
    _continue
    -0.22
    ForeColor
    -0.22
    -dess
    -0.22
    -nil
    -0.22
    åĬ¨çĶŁæĪIJ
    -0.22
    POSITIVE LOGITS
    çļĦè¿ĩç¨ĭ
    0.27
    æ³Ĭ
    0.25
     heal
    0.25
    dot
    0.24
    æĥ°
    0.24
    ợ
    0.24
     Heal
    0.24
     wag
    0.24
     scl
    0.24
    ÃŃst
    0.23
    Activations Density 0.019%

    No Known Activations