© 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. 61258
    Prev
    Next
    INDEX
    Explanations

    authentic and natural

    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
    é»ijæ´ŀ
    -0.09
    éĽªå±±
    -0.09
    æĢ»åħ±
    -0.09
    uos
    -0.09
    åī§çĥĪ
    -0.09
    龸éģĵ
    -0.09
    ç¿ķ
    -0.09
    èĵĭ
    -0.08
    åħ±
    -0.08
    ä¸Ģåħ±
    -0.08
    POSITIVE LOGITS
    èĩªçĦ¶èĢĮ
    0.18
    èĩªçĦ¶
    0.18
    羣å®ŀ
    0.17
    羣å®ŀçļĦ
    0.17
     authenticity
    0.15
    çľŁå¯¦
    0.15
    auth
    0.15
     natural
    0.14
     наÑĤÑĥÑĢ
    0.13
     auth
    0.13
    Activations Density 0.071%

    No Known Activations