© 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. 30572
    Prev
    Next
    INDEX
    Explanations

    attributions and quotes

    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
    6
    -0.09
    1
    -0.08
    棹
    -0.08
    beck
    -0.08
    4
    -0.08
     cater
    -0.08
    èł²
    -0.08
    0
    -0.08
    5
    -0.08
    arm
    -0.08
    POSITIVE LOGITS
    è¿Ļå¥Ĺ
    0.10
    æ»ķ
    0.10
    åľ°è¯´
    0.10
    ä»ĸ说
    0.09
    說
    0.09
    åµ
    0.09
    说çĿĢ
    0.09
    骤
    0.09
    èĶļ
    0.09
    иÑĩно
    0.09
    Activations Density 0.066%

    No Known Activations