© 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. 87445
    Prev
    Next
    INDEX
    Explanations

    Reserved

    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
    MAND
    -0.30
    åıĭè°Ĭ
    -0.26
    kul
    -0.25
    pill
    -0.25
     Wyn
    -0.25
    对ä»ĸ们
    -0.24
    bull
    -0.24
    é¼ĵ
    -0.24
    tabpanel
    -0.24
    æĹº
    -0.24
    POSITIVE LOGITS
    iac
    0.27
    isma
    0.26
    ело
    0.25
    ạy
    0.25
    å®īåħ¨
    0.25
    org
    0.24
     `"
    0.24
    chè
    0.24
     deal
    0.24
     "
    0.24
    Activations Density 0.057%

    No Known Activations