© 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. 56309
    Prev
    Next
    INDEX
    Explanations

    subject

    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
    è²Į
    -0.33
    éªĸ
    -0.27
    æ®ļ
    -0.26
    <Component
    -0.26
    CharCode
    -0.26
    æ»ĭ润
    -0.25
    ä¸Ģåı¥
    -0.24
    COMP
    -0.24
    FileSync
    -0.24
    Capability
    -0.24
    POSITIVE LOGITS
    plies
    0.28
    çĥŁçģ«
    0.27
     ex
    0.27
    pragma
    0.27
    er
    0.26
     dep
    0.26
     knit
    0.25
    çª
    0.25
     among
    0.24
    åĪijæ³ķ
    0.24
    Activations Density 0.014%

    No Known Activations