© 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. 31348
    Prev
    Next
    INDEX
    Explanations

    artillery or guns

    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
    flo
    -0.10
    ç²½
    -0.09
    è¸ıåħ¥
    -0.08
    å·¥ä½ľæĬ¥åijĬ
    -0.08
    踩
    -0.08
    æīij
    -0.08
    é£İæļ´
    -0.08
    èĤ²
    -0.08
     ingr
    -0.08
    åĨľä½ľçī©
    -0.08
    POSITIVE LOGITS
    åıijå°Ħ
    0.11
    hee
    0.10
    å¼¹
    0.10
    çĤ®
    0.10
    éĹªåħī
    0.09
    è½®
    0.09
    å½Ī
    0.09
    دÙĦÙĬÙĦ
    0.09
    ç´§å¼ł
    0.09
    çĻ½èī²
    0.09
    Activations Density 0.184%

    No Known Activations