© 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. 22826
    Prev
    Next
    INDEX
    Explanations

    high-risk

    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
    æī¾åĪ°äºĨ
    -0.09
    çĥĻ
    -0.09
     Kaplan
    -0.09
    ì¼Ģ
    -0.08
    _hr
    -0.08
    纯粹
    -0.08
    nb
    -0.08
     nb
    -0.08
     sample
    -0.08
    åħ³éĶ®æŶåĪ»
    -0.08
    POSITIVE LOGITS
    åīįä¸ĸ
    0.10
    è¡Įä¸ļçļĦ
    0.10
     suspicion
    0.10
    èĢģåŃIJ
    0.10
    åı¯çĸij
    0.09
    æģ»
    0.09
    åı¯æł¹æį®
    0.09
    åı¬
    0.09
     Fans
    0.08
    æĢĢçĸij
    0.08
    Activations Density 0.157%

    No Known Activations