© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 42998
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    æľīä»»ä½ķ
    -0.32
    ä»»ä½ķå½¢å¼ı
    -0.30
    æıĸ
    -0.28
    Brains
    -0.28
     Jeb
    -0.26
    ä»»ä½ķä¸Ģ个
    -0.26
    被æ·ĺæ±°
    -0.25
    äºĨå¤ļå°ij
    -0.25
    /licenses
    -0.24
    IFEST
    -0.24
    POSITIVE LOGITS
     specificity
    0.48
     uniqueness
    0.48
     hardness
    0.47
     completeness
    0.47
     validity
    0.46
     low
    0.46
     affordability
    0.46
    æľīæķĪæĢ§
    0.45
     ease
    0.44
     sophistication
    0.44
    Activations Density 0.011%

    No Known Activations