© 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. 63045
    Prev
    Next
    INDEX
    Explanations

    celebrity names

    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
    ä»Ģä¹ĪåİŁåĽł
    -0.09
    æłijèĦĤ
    -0.09
    èĭį
    -0.08
    åŃĹåı·
    -0.08
     touching
    -0.08
    æ§ĺ
    -0.08
     Smooth
    -0.08
    å¯Įè´µ
    -0.08
    andre
    -0.07
    çĪ·
    -0.07
    POSITIVE LOGITS
    æģĻ
    0.10
    oler
    0.09
    å¤ĸè¯Ń
    0.09
    æĪijçļĦå¿ĥ
    0.09
    ä¸Ģèĩ´
    0.09
    æħ°
    0.09
    éĺ²çģ«
    0.09
    ended
    0.09
    å£ģ纸
    0.09
    etwork
    0.09
    Activations Density 0.014%

    No Known Activations