© 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. 1421
    Prev
    Next
    INDEX
    Explanations

    dictatorship and power

    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
    次è¦ģ
    -0.09
    羣å¿ĥ
    -0.09
    次
    -0.09
    亲åĪĩ
    -0.08
    表çĻ½
    -0.08
    cream
    -0.08
    éľ²
    -0.08
    arde
    -0.08
    å¹³åĩ¡
    -0.08
    æ¿ĢçĥĪ
    -0.08
    POSITIVE LOGITS
    ç»Łæ²»
    0.12
    åIJĽ
    0.12
    åİĭåĪ¶
    0.11
    æĿĥåĬĽ
    0.11
    оÑĩно
    0.11
    è´¢
    0.10
     dictatorship
    0.10
    龸éģĵ
    0.10
    çĭ¬
    0.10
     ruler
    0.10
    Activations Density 0.070%

    No Known Activations