© 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. 7928
    Prev
    Next
    INDEX
    Explanations

    blood

    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
     cut
    -0.29
    icals
    -0.27
     around
    -0.26
    inth
    -0.25
     minim
    -0.25
    ä¹Ŀå·ŀ
    -0.25
    oley
    -0.25
    .flash
    -0.24
    åľ°ä¸ĭ
    -0.24
    thers
    -0.24
    POSITIVE LOGITS
    opcode
    0.28
    人æķ°
    0.26
    rier
    0.26
    çĶij
    0.26
    æ¯ı人
    0.25
    æĵł
    0.24
     Defendant
    0.24
    (Scene
    0.24
     gated
    0.23
     abuses
    0.23
    Activations Density 0.004%

    No Known Activations