© 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. 62174
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    åłķ
    -0.10
    ãģŀ
    -0.08
    çĪ±ä½ł
    -0.08
    éĺĭ
    -0.08
    itet
    -0.08
    _nm
    -0.08
    portal
    -0.08
    enko
    -0.08
     Deferred
    -0.08
    chner
    -0.08
    POSITIVE LOGITS
    /lic
    0.10
    ä¹ĺçĶ¨è½¦
    0.10
    lector
    0.09
    ÑĩаÑģÑĤ
    0.09
    SES
    0.09
    满满
    0.09
    кÑĢа
    0.08
    _PENDING
    0.08
    éĶ¯
    0.08
    楽
    0.08
    Activations Density 0.065%

    No Known Activations