© 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. 24-TRANSCODER-HP
    7. 150597
    Prev
    Next
    INDEX
    Explanations

    awards and honors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     category
    -0.46
    æľĢä½³
    -0.45
     categories
    -0.43
     CATEGORY
    -0.40
     catégorie
    -0.40
    ç±»åĪ«
    -0.40
    åĪĨç±»
    -0.39
     categorÃŃa
    -0.39
     Category
    -0.38
    -category
    -0.38
    POSITIVE LOGITS
    èĭŀ
    0.28
    ç¼ĵ
    0.28
    tm
    0.27
     tụ
    0.26
    éłĨ
    0.25
    顺åºı
    0.25
    æħİ
    0.25
    WithOptions
    0.25
     Arabia
    0.25
    顺
    0.24
    Activations Density 0.920%

    No Known Activations