© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88716
    Prev
    Next
    INDEX
    Explanations

    how and what

    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
    ÑĥÑĤÑĮ
    -0.25
    .unbind
    -0.25
    unbind
    -0.25
     hindsight
    -0.24
     unavoid
    -0.24
    å°¼åħĭ
    -0.24
    æģ³
    -0.23
    unce
    -0.23
    '].$
    -0.23
    idon
    -0.23
    POSITIVE LOGITS
    ?
    0.36
     Magazine
    0.30
    ?↵
    0.30
     junior
    0.29
    ?↵↵
    0.29
    ä¸Ģè¾¹
    0.28
     stem
    0.27
     bridge
    0.27
     TI
    0.27
    bridge
    0.27
    Activations Density 0.042%

    No Known Activations