© 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. 112214
    Prev
    Next
    INDEX
    Explanations

    Communication/Information

    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
     be
    -0.31
    æĺ¯å¤ļä¹Ī
    -0.31
    質
    -0.28
     appear
    -0.27
     have
    -0.26
    -be
    -0.26
     Be
    -0.26
     disrupt
    -0.26
     vacancies
    -0.25
    hé
    -0.25
    POSITIVE LOGITS
    Will
    0.31
    æ½ľèĥ½
    0.30
     WILL
    0.28
    å°Ĩäºİ
    0.27
     Will
    0.27
    便ä¼ļ
    0.26
    éĥ½ä¼ļæľī
    0.26
    å°Ĩåľ¨
    0.25
    ghi
    0.25
    TRL
    0.25
    Activations Density 0.006%

    No Known Activations