© 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. 11307
    Prev
    Next
    INDEX
    Explanations

    against

    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
    驽
    -0.09
    æĶĢçĻ»
    -0.09
    èµ
    -0.09
    ogi
    -0.09
    åĩ¿
    -0.09
    wers
    -0.09
    rz
    -0.08
    бÑĭ
    -0.08
    .tt
    -0.08
    ç¨ĭ度
    -0.08
    POSITIVE LOGITS
     against
    0.28
    against
    0.26
    Against
    0.25
     Against
    0.25
     gegen
    0.22
    对ä»ĺ
    0.19
     ضد
    0.19
     contre
    0.19
     tegen
    0.15
    éĴĪ对
    0.15
    Activations Density 0.156%

    No Known Activations