© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8645
    Prev
    Next
    INDEX
    Explanations

    advice

    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
    æķ
    -0.09
    èĭķ
    -0.09
     SLOT
    -0.08
    .Flat
    -0.08
    衾
    -0.08
    çľĭä¸įåĪ°
    -0.08
    è¡°
    -0.08
    åľ¨å½ĵåľ°
    -0.08
    .BUTTON
    -0.08
    ä»ĭç»įä¸Ģä¸ĭ
    -0.08
    POSITIVE LOGITS
     ÑģовеÑĤ
    0.10
    è§Ħéģ¿
    0.09
    è¿·
    0.09
    çĶ¨èį¯
    0.09
    趣
    0.08
    ARA
    0.08
    失
    0.08
    æĮĩçĤ¹
    0.08
    аÑĨии
    0.08
     advice
    0.08
    Activations Density 0.079%

    No Known Activations