© 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. 7918
    Prev
    Next
    INDEX
    Explanations

    cuts

    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
     MOUSE
    -0.26
     incontr
    -0.25
     primitives
    -0.25
    åıijçĥŃ
    -0.25
    Converted
    -0.25
    -anchor
    -0.24
    tre
    -0.24
    uis
    -0.24
     endors
    -0.24
    çĻ»åľº
    -0.24
    POSITIVE LOGITS
    unker
    0.28
    ÑģÑĤв
    0.27
     sever
    0.26
    Ñĩив
    0.26
    cent
    0.26
    icut
    0.26
     hem
    0.26
    èĢ¿
    0.25
    esi
    0.25
     worker
    0.25
    Activations Density 0.010%

    No Known Activations