© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 52313
    Prev
    Next
    INDEX
    Explanations

    Roger Moore, Styles, Fast Five

    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
    è´º
    -0.10
    çļİ
    -0.10
    对她
    -0.10
    åıĺéĢŁ
    -0.09
    沤
    -0.09
    è·ĭ
    -0.09
    çĤ«
    -0.09
    èĩªè´¸
    -0.09
    æķijçģ¾
    -0.09
     tard
    -0.09
    POSITIVE LOGITS
    oman
    0.09
    æĶ¯æŁ±
    0.08
    èģĬ
    0.08
    stu
    0.08
    office
    0.08
    udas
    0.08
     diff
    0.08
    outine
    0.08
    管çIJĨå±Ģ
    0.08
    åĽ¢
    0.08
    Activations Density 0.005%

    No Known Activations