© 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. 58359
    Prev
    Next
    INDEX
    Explanations

    her

    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
    acco
    -0.33
    ä¼Ĺ人
    -0.29
     humans
    -0.28
     teams
    -0.28
    人们
    -0.28
     Cru
    -0.28
     beings
    -0.27
    ','',
    -0.27
     people
    -0.26
    icans
    -0.26
    POSITIVE LOGITS
    ä¸ĸçķĮä¸Ģæµģ
    0.27
    æĢħ
    0.27
    uy
    0.27
     pragma
    0.27
    æIJŀ
    0.26
    ãĤ¹ãĥŀ
    0.26
    çĩĥæ²¹
    0.25
    ResourceId
    0.25
    oni
    0.25
    qh
    0.25
    Activations Density 0.000%

    No Known Activations