© 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. 27-TRANSCODER-HP
    7. 56485
    Prev
    Next
    INDEX
    Explanations

    thread

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çĶ©
    -0.26
    avar
    -0.24
    ża
    -0.23
    æĹłæīĢ
    -0.23
     ****************************************************************
    -0.23
    ortic
    -0.23
    _tok
    -0.23
     moll
    -0.23
     OCC
    -0.22
    ĸī
    -0.22
    POSITIVE LOGITS
     invers
    0.26
    tere
    0.25
    -inverse
    0.24
    sa
    0.24
    çĬ¶
    0.24
    并ä¸į代表
    0.23
     destruct
    0.23
    æIJģ
    0.23
    /false
    0.23
    éĤ£æł·çļĦ
    0.23
    Activations Density 0.125%

    No Known Activations