© 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. 7696
    Prev
    Next
    INDEX
    Explanations

    specific individual

    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
    anker
    -0.26
    ayer
    -0.26
    åIJįçīĩ
    -0.26
    主èIJ¥
    -0.25
    å·ŀå¸Ĥ
    -0.25
    acked
    -0.25
    asure
    -0.25
    åī¯ä¸»ä»»
    -0.25
    èģĶç³»æĸ¹å¼ı
    -0.24
    acker
    -0.23
    POSITIVE LOGITS
     specific
    1.20
     particular
    1.18
    çī¹å®ļ
    1.13
     individual
    1.04
     Specific
    1.00
    åħ·ä½ĵ
    0.94
    specific
    0.92
     конкÑĢеÑĤ
    0.91
     Individual
    0.89
    Specific
    0.88
    Activations Density 0.001%

    No Known Activations