© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19450
    Prev
    Next
    INDEX
    Explanations

    pointed a handgun in his face

    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
    å¾¹
    -0.09
    è²Į
    -0.09
    å½»
    -0.09
    _cp
    -0.08
    éĻį
    -0.08
    带çĿĢ
    -0.08
    åħ¶æīĢ
    -0.08
    ä½łä¼ļåıijçİ°
    -0.08
    elder
    -0.08
    Intl
    -0.08
    POSITIVE LOGITS
    èĢ³è¾¹
    0.11
    è´´è¿ij
    0.11
    èĥ¸åı£
    0.11
    åĩij
    0.10
    讣
    0.09
     ÑĢаÑģÑģ
    0.09
    iah
    0.09
    æľ¬èº«çļĦ
    0.09
    èĥ¸åīį
    0.08
    anos
    0.08
    Activations Density 0.039%

    No Known Activations