© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48165
    Prev
    Next
    INDEX
    Explanations

    packed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è®·
    -0.10
    enis
    -0.09
    缱
    -0.09
    åħ¬çĦ¶
    -0.09
    æ¡Ī
    -0.09
    åĵij
    -0.08
    åĬŁè¯¾
    -0.08
     Wichita
    -0.08
    æĭ¿æĿ¥
    -0.08
     Antar
    -0.08
    POSITIVE LOGITS
    æĮ¤
    0.12
     packed
    0.12
    packed
    0.11
     packing
    0.11
    æĮ¤åİĭ
    0.11
    æĵł
    0.10
    åİĭ缩
    0.10
    .pack
    0.10
    packing
    0.10
    åİĭè¿«
    0.10
    Activations Density 0.258%

    No Known Activations