© 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. 19672
    Prev
    Next
    INDEX
    Explanations

    nestled, cuddled, huddle

    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
    sville
    -0.09
    è¹Ħ
    -0.08
    jie
    -0.08
    ä½ľé£İ
    -0.08
    .gg
    -0.08
    house
    -0.08
    ASTER
    -0.08
    å¹¹
    -0.08
     tro
    -0.08
    éľĩ
    -0.07
    POSITIVE LOGITS
    åĴª
    0.11
    åľ¨ä¸Ģèµ·
    0.10
    åı¤åħ¸
    0.10
    elage
    0.10
    åľ»
    0.10
    çĶ¸
    0.09
    ä¾¦å¯Ł
    0.09
    å¸Ľ
    0.09
    çĪ±å¥½
    0.09
    âľ©
    0.09
    Activations Density 0.006%

    No Known Activations