© 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. 97488
    Prev
    Next
    INDEX
    Explanations

    Quantities and measurements

    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
     subt
    -0.27
    æĹ¢
    -0.27
    çķ´
    -0.26
    åİŁæłĩé¢ĺ
    -0.26
    صر
    -0.26
    å¼Ģå±Ģ
    -0.26
     whatsoever
    -0.25
    ucken
    -0.25
     Org
    -0.25
    OLON
    -0.25
    POSITIVE LOGITS
    èĬ³
    0.26
    çĺª
    0.26
     herald
    0.25
     wicked
    0.23
    åij½
    0.23
    顯
    0.23
     Massive
    0.23
    cock
    0.23
    æ´Ĺ
    0.23
    igrants
    0.23
    Activations Density 0.055%

    No Known Activations