© 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. 112649
    Prev
    Next
    INDEX
    Explanations

    digits

    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
     EITHER
    -0.27
    ither
    -0.26
    ONUS
    -0.24
     mate
    -0.24
    å®ģ
    -0.24
     cakes
    -0.24
     bunker
    -0.24
     Parcelable
    -0.23
    æĬķåħ¥
    -0.23
     Horm
    -0.23
    POSITIVE LOGITS
     critical
    0.25
    çľ¼ä¸ĭ
    0.24
    fant
    0.24
    .Adapter
    0.24
     fif
    0.24
    è¿ľæĸ¹
    0.23
     Wh
    0.23
     ÑĦ
    0.23
    ä¸Ģä¸Ŀ
    0.23
    è¿ĻçĤ¹
    0.23
    Activations Density 0.010%

    No Known Activations