© 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. 32-TRANSCODER-HP
    7. 41194
    Prev
    Next
    INDEX
    Explanations

    energy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canton
    -0.27
    umu
    -0.27
     Harbor
    -0.26
    èįĥ
    -0.24
    æµĩæ°´
    -0.24
    inger
    -0.23
    åŀĵ
    -0.23
    å¹´çĶ±
    -0.23
     xamarin
    -0.22
    èį¯æĿIJ
    -0.22
    POSITIVE LOGITS
     energy
    1.88
    èĥ½éĩı
    1.65
    energy
    1.61
    Energy
    1.59
     Energy
    1.59
    -energy
    1.45
    _energy
    1.45
    èĥ½æºIJ
    1.45
     energies
    1.42
    çļĦèĥ½éĩı
    1.39
    Activations Density 0.002%

    No Known Activations