© 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. 39254
    Prev
    Next
    INDEX
    Explanations

    time remaining or elapsed

    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
    _SETUP
    -0.10
    åħ»èĤ²
    -0.10
    çĪ±äºº
    -0.10
    åīįç½®
    -0.09
    loser
    -0.09
    èĩªç§°
    -0.09
    èįĨ
    -0.09
    å¹ķ
    -0.09
    éĽ¾
    -0.09
    inen
    -0.09
    POSITIVE LOGITS
    éĻį
    0.09
    ORT
    0.08
    æĹº
    0.08
    ury
    0.08
    isl
    0.07
    ä¸įåĪ©äºİ
    0.07
    ä¸ĭåįķ
    0.07
    è¿ĩå¤ļ
    0.07
     coh
    0.07
    OrDefault
    0.07
    Activations Density 0.003%

    No Known Activations