© 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. 58287
    Prev
    Next
    INDEX
    Explanations

    on

    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
    Not in Any Lists

    No Comments

    Negative Logits
    blr
    -0.34
    ored
    -0.26
    éĶ»çĤ¼
    -0.26
    ода
    -0.26
     women
    -0.26
    çļĦåģļæ³ķ
    -0.25
    çĶŁæ´»çļĦ
    -0.25
    主ä½ĵ
    -0.25
    ðĿijī
    -0.25
     Inc
    -0.24
    POSITIVE LOGITS
    ä¸ĩåħĥ以ä¸Ĭ
    0.27
    åİŁåĽłä¹ĭä¸Ģ
    0.26
    åĸĩ
    0.25
    bü
    0.25
    isable
    0.25
     disclose
    0.25
    buch
    0.25
    æİ¥çĿĢ
    0.24
    æĭĽèĤ¡
    0.24
    ager
    0.24
    Activations Density 0.004%

    No Known Activations