© 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. 39227
    Prev
    Next
    INDEX
    Explanations

    not help

    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¦ģèĢĥèĻij
    -0.11
    AGED
    -0.10
    æľīç§į
    -0.10
    èĪįå¾Ĺ
    -0.10
    OTOS
    -0.10
    entric
    -0.10
    orns
    -0.10
    ODB
    -0.10
    è¾ĵç»Ļ
    -0.09
    çĺ´
    -0.09
    POSITIVE LOGITS
    åĬŀæ³ķ
    0.13
    解åĨ³éĹ®é¢ĺ
    0.13
    帮åĬ©
    0.13
     помог
    0.12
     help
    0.11
    æķĪæŀľ
    0.11
    å¥ı
    0.11
    æĭ¯æķij
    0.11
    解åĨ³
    0.10
     helpful
    0.10
    Activations Density 0.128%

    No Known Activations