© 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. 27256
    Prev
    Next
    INDEX
    Explanations

    absence or without

    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
    /widget
    -0.10
    èĢĮéĿŀ
    -0.10
    åĿĬ
    -0.09
    ÑĢаж
    -0.09
    EDIA
    -0.09
    TÄ°
    -0.09
    èģĮè´£
    -0.09
    æ©IJ
    -0.09
    æ²ĥå°Ķ
    -0.09
    æĻĶ
    -0.09
    POSITIVE LOGITS
    adin
    0.10
    çĥŃæĥħ
    0.08
     unavailable
    0.08
    çĶ±äºİ
    0.08
    pc
    0.08
     due
    0.08
    缺å¸Ń
    0.07
    ç¥İ
    0.07
    çļĦçĥŃæĥħ
    0.07
    èĦļæŃ¥
    0.07
    Activations Density 0.039%

    No Known Activations