© 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. 33997
    Prev
    Next
    INDEX
    Explanations

    writing for creative/technical contexts

    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
    âĢIJ
    -0.11
    util
    -0.08
    âĢ
    -0.08
    ev
    -0.08
    åķĦ
    -0.08
    Âł
    -0.08
    çĴİ
    -0.08
    ’
    -0.08
    epar
    -0.07
    eref
    -0.07
    POSITIVE LOGITS
    Č
    0.14
    ,...↵
    0.11
    ä¹łè¿ijå¹³æĢ»
    0.11
    [âĢ¦
    0.11
    åİŁæłĩé¢ĺ
    0.10
    \↵
    0.10
    ç¶ļãģįãĤĴèªŃãĤĢ
    0.10
     ...↵↵
    0.10
    åĽłåľ°åĪ¶
    0.10
    æŁ¥çľĭåħ¨æĸĩ
    0.10
    Activations Density 0.423%

    No Known Activations