© 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. 21791
    Prev
    Next
    INDEX
    Explanations

    damage and destruction

    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
    éĢīè´Ń
    -0.09
    .pad
    -0.09
    太空
    -0.09
    ä»»ä½ķæŶåĢĻ
    -0.08
    åįģä¸īå±Ĭ
    -0.08
     Sherman
    -0.08
    象
    -0.08
    æIJŀ好
    -0.08
    åŀ¢
    -0.08
     tÃł
    -0.08
    POSITIVE LOGITS
    ÇĶ
    0.10
    èĬĬ
    0.09
    homes
    0.09
    æį
    0.09
    ä¸Ģå¤ľ
    0.09
    糧
    0.09
    å¢ŀå¹ħ
    0.09
    èĶ¬
    0.09
    ASA
    0.08
    ACHI
    0.08
    Activations Density 0.043%

    No Known Activations