© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10501
    Prev
    Next
    INDEX
    Explanations

    gene delivery efficiency

    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
    éļıæŶéļıåľ°
    -0.10
     обÑĭ
    -0.09
    ä¸ī代
    -0.09
    нÑĤ
    -0.09
    è¡ĮæĶ¿å®¡æī¹
    -0.09
    çī¹æĿĥ
    -0.09
    çIJ¯
    -0.09
    å±ŀäºİèĩªå·±
    -0.09
    åĩºåħ·
    -0.08
    æŃ£å®Ĺ
    -0.08
    POSITIVE LOGITS
    ä¿¡ä»»
    0.09
    ä¸Ģåij³
    0.08
    иÑĩеÑģким
    0.08
     Heard
    0.08
    zá
    0.08
     Ksi
    0.08
    禧
    0.08
    ç¯Ļ
    0.08
    ç©¿
    0.08
    èģĮä¸ļ
    0.08
    Activations Density 0.081%

    No Known Activations