© 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. 32312
    Prev
    Next
    INDEX
    Explanations

    rent, rental, hire, lease

    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
    ä¸ĩ家
    -0.09
    ä¹īåĬ¡
    -0.09
    ä¸ŃåĽ½èģĶéĢļ
    -0.09
    è¡¥
    -0.08
    åħ¬åijĬ
    -0.08
    ä¸įæŃ»
    -0.08
    éĻµ
    -0.08
    andel
    -0.08
    ç³ĸæŀľ
    -0.08
    anchor
    -0.08
    POSITIVE LOGITS
     Renew
    0.10
     Rentals
    0.10
    éĢIJ
    0.10
     rentals
    0.10
    çĶ¨è½¦
    0.09
     rental
    0.09
    éŨ
    0.09
    赶
    0.09
    èĥ½æĬĬ
    0.09
     Rental
    0.08
    Activations Density 0.223%

    No Known Activations