© 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. 130272
    Prev
    Next
    INDEX
    Explanations

    the

    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
    upt
    -0.24
    çĺ¿
    -0.24
    èħ±
    -0.24
    upe
    -0.24
    ippers
    -0.24
    å·¡
    -0.24
     Tem
    -0.24
     richness
    -0.23
    tá
    -0.23
     viz
    -0.23
    POSITIVE LOGITS
    (fe
    0.27
    åİŁå§ĭ
    0.25
    ating
    0.24
    esty
    0.23
    fter
    0.23
    ẳng
    0.23
    _while
    0.23
    æ´ĭ
    0.23
     Muss
    0.23
    çļĦæĥħ绪
    0.23
    Activations Density 0.002%

    No Known Activations