© 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. 34263
    Prev
    Next
    INDEX
    Explanations

    saving money on

    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
    èĭ£
    -0.09
    ä½ľåĵģåĨħ容
    -0.09
     doubt
    -0.09
    æµĵåİļ
    -0.09
    -offset
    -0.08
     Wildlife
    -0.08
    èĪªçº¿
    -0.08
    æīŃ转
    -0.08
    æİĴæ°´
    -0.08
    产éĶĢ
    -0.08
    POSITIVE LOGITS
    ä»İæĿ¥ä¸į
    0.11
    ä»İæĿ¥æ²¡æľī
    0.09
    åĪij
    0.09
    èĢĹ
    0.09
    åħ¹
    0.08
    _DM
    0.08
    umes
    0.08
    enza
    0.08
    çĽijæĬ¤
    0.08
    _GU
    0.08
    Activations Density 0.040%

    No Known Activations