© 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. 3374
    Prev
    Next
    INDEX
    Explanations

    stretch of road

    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
    ocom
    -0.09
    iston
    -0.09
    æĺĤ
    -0.08
    enz
    -0.08
     WTF
    -0.08
    çĦ¶æĺ¯
    -0.08
    æ¦ľ
    -0.08
    kel
    -0.08
    GEN
    -0.08
    iken
    -0.08
    POSITIVE LOGITS
    å¸ļ
    0.10
    粮油
    0.10
    abouts
    0.09
    åĽłåľ°
    0.09
    æĹłå¿§
    0.09
    å·¥ä½ľä¸Ń
    0.09
    /high
    0.09
    ÐĽÐIJ
    0.09
    /default
    0.08
    认æ¸ħ
    0.08
    Activations Density 0.004%

    No Known Activations