© 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. 61557
    Prev
    Next
    INDEX
    Explanations

    records and documentation

    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
    æĪij们认为
    -0.12
    nowled
    -0.09
    åĥ
    -0.09
    éĥ½è®¤ä¸º
    -0.09
    aly
    -0.09
    thern
    -0.09
    éĹ»
    -0.08
    éĻĤ
    -0.08
    alan
    -0.08
    èģŀ
    -0.08
    POSITIVE LOGITS
    è®°å½ķ
    0.15
    纪å½ķ
    0.14
     records
    0.13
     documentation
    0.12
     record
    0.12
    è¨ĺéĮĦ
    0.12
    è®°è½½
    0.11
     dokument
    0.10
    åı°è´¦
    0.10
    (records
    0.10
    Activations Density 0.059%

    No Known Activations