© 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. 48300
    Prev
    Next
    INDEX
    Explanations

    describing the situation

    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
    æĢ§å¼º
    -0.10
    åĬŁçĶ¨
    -0.09
    å®Īä½ı
    -0.09
    æ©
    -0.09
    å¾ģæ±Ĥ
    -0.09
    é¤
    -0.09
    åµİ
    -0.09
    èķĥ
    -0.09
    åī¡
    -0.09
    é£İéĩĩ
    -0.09
    POSITIVE LOGITS
     situation
    0.26
    å±ĢåĬ¿
    0.21
    å½¢åĬ¿
    0.20
     Situation
    0.20
     situations
    0.18
    æĥħåĨµ
    0.18
    çĬ¶åĨµ
    0.18
    å¤Ħå¢ĥ
    0.18
     situación
    0.17
    å±ĢéĿ¢
    0.17
    Activations Density 0.040%

    No Known Activations