© 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. 97416
    Prev
    Next
    INDEX
    Explanations

    Website paths

    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
    纳æĸ¯
    -0.28
    na
    -0.27
    åħ¬å¸ĥäºĨ
    -0.27
    åıijå±ķä¸Ń
    -0.26
    åľŁèĢ³
    -0.25
    èĴ¯
    -0.25
    encies
    -0.25
     sue
    -0.25
    è¿Ļæĺ¯ä¸Ģç§į
    -0.24
    iard
    -0.23
    POSITIVE LOGITS
    erdem
    0.30
    æ¤Ĵ
    0.29
    иÑĤеÑĤ
    0.27
    aÄŁ
    0.26
    #echo
    0.25
    _-_
    0.25
     Barrett
    0.25
    æīĴ
    0.25
     CONSTANTS
    0.25
    ",__
    0.24
    Activations Density 0.009%

    No Known Activations