© 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. 35541
    Prev
    Next
    INDEX
    Explanations

    plans for future projects

    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
    æĶ¾åѦ
    -0.10
    urat
    -0.10
    俪
    -0.09
    第ä¸Ģ次
    -0.09
    inar
    -0.09
    ataka
    -0.09
    éģĩè§ģ
    -0.08
    çݩ游æĪı
    -0.08
    红è±Ĩ
    -0.08
    ç»ıè¿ĩå¤ļå¹´
    -0.08
    POSITIVE LOGITS
     plans
    0.23
    计åĪĴ
    0.21
    plans
    0.20
     Plans
    0.18
    è¨ĪåĬĥ
    0.17
     план
    0.16
    æľªæĿ¥
    0.16
    Plans
    0.16
     plan
    0.16
    æīĵç®Ĺ
    0.15
    Activations Density 0.062%

    No Known Activations