© 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. 18342
    Prev
    Next
    INDEX
    Explanations

    many things

    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
    ADI
    -0.09
    åħ·
    -0.09
    ACHI
    -0.09
    ROTO
    -0.09
    æ²¼
    -0.08
    imate
    -0.08
    çıįæĥľ
    -0.08
    è¿ŀå¿Ļ
    -0.08
    æĢ¥äºİ
    -0.08
    minated
    -0.08
    POSITIVE LOGITS
    ä¸įèµ·
    0.09
    åĬĽæ±Ĥ
    0.09
    æĪIJ年人
    0.08
     Krish
    0.08
    å°Ķæĸ¯
    0.08
    coli
    0.08
    éĺĹ
    0.08
    è°ħ
    0.08
    uh
    0.08
    çĽĨ
    0.07
    Activations Density 0.045%

    No Known Activations