© 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. 18-TRANSCODER-HP
    7. 90256
    Prev
    Next
    INDEX
    Explanations

    terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æľīçĶ¨
    -0.34
    ↵↵↵
    -0.30
    è¿Ļ个éĹ®é¢ĺ
    -0.29
     useful
    -0.28
     Fr
    -0.26
    ç»Ŀ对
    -0.26
    èĤĺ
    -0.26
    Fr
    -0.26
    ↵
    -0.25
     Bah
    -0.25
    POSITIVE LOGITS
    ólogo
    0.27
    RuleContext
    0.27
    åıĹéĻIJ
    0.27
    GenerationStrategy
    0.26
    assium
    0.26
    çĽ²
    0.25
    ä¸ĩåı°
    0.24
    .Decimal
    0.24
    erosis
    0.24
    ãĤĭãģ®ãģ¯
    0.24
    Activations Density 35.326%

    No Known Activations