© 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. 6745
    Prev
    Next
    INDEX
    Explanations

    travel or excursion

    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
    çīĮåŃIJ
    -0.09
    æ¦ķ
    -0.09
    itra
    -0.08
    ifes
    -0.08
    åłĤ
    -0.08
    deviceId
    -0.08
    æŃ¤ä¸¾
    -0.08
    ÑĥÑĢ
    -0.08
    çĨĻ
    -0.08
    éĽī
    -0.08
    POSITIVE LOGITS
     ngũ
    0.09
    ÙħاÙħ
    0.08
    anja
    0.08
    æĥħ人
    0.08
    SourceType
    0.08
    oman
    0.08
    ẻ
    0.08
    èĥ½åľ¨
    0.08
    _CI
    0.08
     Baylor
    0.08
    Activations Density 0.002%

    No Known Activations