© 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. 23820
    Prev
    Next
    INDEX
    Explanations

    ice cream

    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
    edList
    -0.12
    å¼¯æĽ²
    -0.10
    äºĽä»Ģä¹Ī
    -0.09
    ether
    -0.09
    ä¸Ģè§Ī
    -0.09
    åĬ£
    -0.09
    æ¶Ľ
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    æīĵåĵį
    -0.09
    潤
    -0.09
    POSITIVE LOGITS
    mediate
    0.09
     giver
    0.09
    èŀįåĮĸ
    0.08
     maker
    0.08
    mobile
    0.08
    -maker
    0.08
    oola
    0.08
    isode
    0.08
    apult
    0.08
     Maker
    0.08
    Activations Density 0.005%

    No Known Activations