© 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. 30-TRANSCODER-HP
    7. 95845
    Prev
    Next
    INDEX
    Explanations

    science/biology articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fusion
    -0.37
    èŀįåIJĪ
    -0.34
    genes
    -0.31
     fused
    -0.31
     Fusion
    -0.30
    gene
    -0.29
    èŀį
    -0.28
    æįķ
    -0.28
     gene
    -0.28
    vet
    -0.28
    POSITIVE LOGITS
     Express
    0.29
     slick
    0.28
     oscillator
    0.26
     Counter
    0.26
    HttpServletRequest
    0.25
     expression
    0.25
    ÅĽwiad
    0.25
    sa
    0.25
     counter
    0.24
     Sadd
    0.24
    Activations Density 0.988%

    No Known Activations