© 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. 51335
    Prev
    Next
    INDEX
    Explanations

    mailing list, mailed survey

    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
    idge
    -0.10
    æĶ¯
    -0.08
    ÑĦÑĢ
    -0.08
    leÅŁtirme
    -0.08
    èµ·
    -0.08
     Berm
    -0.08
    иÑĢÑĥ
    -0.08
    pets
    -0.08
    i
    -0.08
    ething
    -0.07
    POSITIVE LOGITS
    äºĨä¸Ģ份
    0.11
    鼶è·Ŀ离
    0.09
    ãģ¾ãģĦ
    0.09
    ear
    0.09
     sunset
    0.09
    artner
    0.09
    ãĤĤãģ®ãģ®
    0.08
    æĪIJåijĺ
    0.08
    eks
    0.08
    ffective
    0.08
    Activations Density 0.002%

    No Known Activations