© 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. 3350
    Prev
    Next
    INDEX
    Explanations

    flight sim controller attendant physiology departments

    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
    nts
    -0.10
    éĺµåľ°
    -0.09
    äºĭåĦ¿
    -0.09
    è¯īæ±Ĥ
    -0.09
    ities
    -0.09
    ference
    -0.09
    SION
    -0.09
    è¹ĩ
    -0.09
    缸çĪ±
    -0.09
    æ°´æµģ
    -0.09
    POSITIVE LOGITS
    ary
    0.11
    seeing
    0.10
    mare
    0.09
    ÑĢаÑģ
    0.09
    èľ®
    0.08
    unes
    0.08
    çģ¾åĮº
    0.08
    нем
    0.08
    elter
    0.08
    æĢ»çĽij
    0.08
    Activations Density 0.010%

    No Known Activations