© 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. 112800
    Prev
    Next
    INDEX
    Explanations

    helpers, servants

    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
    ilo
    -0.28
    åij½è¿IJ
    -0.28
    åĴ½
    -0.27
     distortion
    -0.26
    åŁĭ
    -0.25
    Contained
    -0.24
    éĹŃ
    -0.24
    ä¸ĸ
    -0.24
    response
    -0.24
    大
    -0.24
    POSITIVE LOGITS
    级以ä¸Ĭ
    0.26
    ä¸Ńéĵģ
    0.26
    ünde
    0.25
    -under
    0.25
    ÐŁÑĢо
    0.24
    chaft
    0.24
    ç²¾ç»ĨåĮĸ
    0.23
     accompanying
    0.23
    .TXT
    0.23
    ä¸Ńä¿Ħ
    0.23
    Activations Density 0.020%

    No Known Activations