© 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. 34122
    Prev
    Next
    INDEX
    Explanations

    rodents and pests

    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
    绿èĮ¶
    -0.09
    诳
    -0.09
    æį¶
    -0.09
    樱èĬ±
    -0.08
    æĮĸ
    -0.08
    _recovery
    -0.08
    绣çŃ¹æİ¨è¿Ľ
    -0.08
     tod
    -0.08
    èħ°éĥ¨
    -0.08
    绺
    -0.08
    POSITIVE LOGITS
    为æ°ij
    0.11
    大åݦ
    0.09
    éĽı
    0.09
    wayne
    0.09
    åĩºå¤Ħ
    0.09
    rats
    0.09
    æIJ¬å®¶
    0.09
    èĽŁ
    0.09
    ç¦ģ
    0.09
    çĻ»
    0.09
    Activations Density 0.129%

    No Known Activations