© 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. 7713
    Prev
    Next
    INDEX
    Explanations

    code

    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
     zij
    -0.32
    æ¦Ľ
    -0.26
    оÑĩки
    -0.25
    Ïĩ
    -0.25
     behaves
    -0.25
    æį¨ãģ¦
    -0.24
    å°ijæķ°
    -0.24
     construed
    -0.23
     treason
    -0.23
    åħ·ä½ĵæĥħåĨµ
    -0.23
    POSITIVE LOGITS
     IonicModule
    0.28
    yh
    0.28
    łĢ
    0.26
     wakeup
    0.25
    -camera
    0.25
    &P
    0.25
    -yard
    0.24
    éĽĨæĪIJ
    0.23
    çī¢
    0.23
     roman
    0.23
    Activations Density 0.001%

    No Known Activations