© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51162
    Prev
    Next
    INDEX
    Explanations

    was/were followed by nouns

    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
    å½ĵæŶ
    -0.10
    å½ĵå¹´
    -0.10
    æĸ°äºº
    -0.09
    å½ĵæŶçļĦ
    -0.09
    ä¸ļ
    -0.09
    hone
    -0.09
    åĤįæĻļ
    -0.09
    çķ¶æĻĤ
    -0.09
    ÑĦÑĤ
    -0.09
    éĤ£æ¬¡
    -0.09
    POSITIVE LOGITS
    åķ·
    0.09
    è¾IJå°Ħ
    0.09
    æĺİæĺİ
    0.09
    åĪĿå¿ĥ
    0.08
    umatic
    0.08
    è´¹
    0.08
    éĿ©
    0.08
    æľĢéĩįè¦ģçļĦ
    0.08
    izzes
    0.08
     hit
    0.08
    Activations Density 0.119%

    No Known Activations