© 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. 9704
    Prev
    Next
    INDEX
    Explanations

    creative works

    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
     everywhere
    -0.28
    inke
    -0.26
     target
    -0.25
    ä¹ĭæīĢ
    -0.25
    å²Ľå±¿
    -0.25
    ue
    -0.24
    pane
    -0.24
     Target
    -0.24
    pressed
    -0.24
     reverse
    -0.24
    POSITIVE LOGITS
    说åĩºæĿ¥
    0.28
     realidad
    0.27
    çĶ³æĬ¥
    0.26
     imperfect
    0.25
    æĥ«
    0.24
    é£ŀæī¬
    0.24
    GetY
    0.23
    çĴĩ
    0.23
     limitation
    0.23
     Aquarium
    0.23
    Activations Density 0.000%

    No Known Activations