© 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. 150520
    Prev
    Next
    INDEX
    Explanations

    Non-English or code snippets

    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
    çĬ¶
    -0.30
    å±ĤéĿ¢
    -0.29
    {}\
    -0.28
    æĸ¹éĿ¢çļĦ
    -0.28
    {}]
    -0.28
    åĪĩåħ¥çĤ¹
    -0.27
    æĢ§å¼º
    -0.26
    ç²¾çģµ
    -0.25
    æĸ¹éĿ¢
    -0.25
    æĺ§
    -0.25
    POSITIVE LOGITS
    emann
    0.28
    åħ·ä½ĵ
    0.27
    çݰ代
    0.26
    巨大
    0.26
    æ²Ļ
    0.26
     statt
    0.26
     spécialisé
    0.25
    nat
    0.25
    æľĢè¿ij
    0.25
     nat
    0.24
    Activations Density 0.979%

    No Known Activations