© 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. 37737
    Prev
    Next
    INDEX
    Explanations

    . Introduction

    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
    erca
    -0.09
    loy
    -0.08
    èĪįä¸įå¾Ĺ
    -0.08
    è§ĴéĢIJ
    -0.08
    åıįæĬĹ
    -0.08
     Bun
    -0.08
    lamp
    -0.07
    被æ·ĺæ±°
    -0.07
     guru
    -0.07
    ä¸į论
    -0.07
    POSITIVE LOGITS
    ä¸įè´Ł
    0.10
    æĭĸ
    0.09
    èī°
    0.09
    ä¸Ģçľĭ
    0.09
     Ank
    0.09
    ÑĭÑĤа
    0.09
    æĬķåħ¥åĪ°
    0.08
    _SENSOR
    0.08
    æķ¬è¯·
    0.08
    awner
    0.08
    Activations Density 0.027%

    No Known Activations