© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29702
    Prev
    Next
    INDEX
    Explanations

    Texas Rangers or park ranger

    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
    ç»
    -0.10
    åĦ¿
    -0.09
    çĦ¶æĺ¯
    -0.09
    èĢģ人家
    -0.09
    èŁ
    -0.09
    ophil
    -0.09
    neath
    -0.09
    丰ç¡ķ
    -0.09
    èĥ¡åŃIJ
    -0.08
    è¿ĽéŨ
    -0.08
    POSITIVE LOGITS
    ankan
    0.09
    ism
    0.09
    /off
    0.09
    hots
    0.09
    etheless
    0.09
    ues
    0.09
    anca
    0.09
    ×ķת
    0.08
    maid
    0.08
    åħ¶éĹ´
    0.08
    Activations Density 0.004%

    No Known Activations