© 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. 61133
    Prev
    Next
    INDEX
    Explanations

    well followed by adjectives

    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
    å·¡è§Ĩ
    -0.10
    è¿Ļå¥Ĺ
    -0.10
    çĻ½éĵ¶
    -0.09
    åºŃ
    -0.09
    пеÑĩаÑĤ
    -0.09
    é£İæĻ¯
    -0.09
    åī©ä¸ĭçļĦ
    -0.09
    çķĶ
    -0.08
    osit
    -0.08
    åľĪåŃIJ
    -0.08
    POSITIVE LOGITS
    Æ°á»Ľ
    0.09
    ahead
    0.09
    梧
    0.09
    ish
    0.08
    nes
    0.08
    åıĤ
    0.08
    ä»İæł¹æľ¬
    0.08
    osti
    0.08
     toes
    0.08
    æģ¤
    0.08
    Activations Density 0.015%

    No Known Activations