© 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. 3928
    Prev
    Next
    INDEX
    Explanations

    after a day

    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
    æİĩ
    -0.10
    ä¸įæĪIJ
    -0.09
    éĢģåĪ°
    -0.09
    è½®
    -0.09
    车åŀĭ
    -0.09
    ä¸ļçķĮ
    -0.09
    æľªæĪIJ
    -0.09
    EDIA
    -0.09
    äºĮ线
    -0.08
    DSP
    -0.08
    POSITIVE LOGITS
    ç´¯äºĨ
    0.10
    丰ç¡ķ
    0.09
     оÑĩеÑĢед
    0.09
    è¿Ļä¹Īä¹ħ
    0.09
    å°ıæŶåīį
    0.08
    æĪijä¼ļ
    0.08
    è¾Ľåĭ¤
    0.08
    çĸ²æĥ«
    0.08
    ÑĤÑĢÑĥд
    0.08
    åĽŀåij³
    0.08
    Activations Density 0.064%

    No Known Activations