© 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. 111323
    Prev
    Next
    INDEX
    Explanations

    1

    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
    edImage
    -0.26
    woke
    -0.26
    rone
    -0.26
    emens
    -0.26
    ⾦
    -0.26
    ++.
    -0.25
    hare
    -0.25
    ìŀĦ
    -0.25
    kos
    -0.24
    habi
    -0.24
    POSITIVE LOGITS
    ja
    0.28
     term
    0.25
     schl
    0.24
    sphere
    0.24
    redit
    0.24
    cli
    0.24
     Narrow
    0.23
    å¤ļ彩
    0.23
    æ§Ľ
    0.23
    abs
    0.23
    Activations Density 0.087%

    No Known Activations