© 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. 111283
    Prev
    Next
    INDEX
    Explanations

    code snippets and filepaths

    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
    èģĶ
    -0.35
    .openConnection
    -0.28
    èģ¯
    -0.26
    -Headers
    -0.25
    porate
    -0.25
     por
    -0.25
    -touch
    -0.24
    (mi
    -0.24
    å¤įåį°
    -0.24
    otropic
    -0.23
    POSITIVE LOGITS
     каÑĤал
    0.26
    ä¸įä¸Ģå®ļ
    0.25
    楼ä¸ĭ
    0.25
    åı¯æĥľ
    0.25
    ç«ĭæĸ¹
    0.24
    etting
    0.24
    该æĢİä¹ĪåĬŀ
    0.24
    ä¸Ģ代
    0.24
    è¿ĺéľĢ
    0.24
    éļıæīĭ
    0.24
    Activations Density 0.001%

    No Known Activations