© 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. 31378
    Prev
    Next
    INDEX
    Explanations

    transfer into a storage

    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
    ç³»
    -0.10
     Burnett
    -0.09
    åij¼
    -0.08
    大家éĥ½
    -0.08
    itech
    -0.08
    ä½ĵ系建设
    -0.08
    rien
    -0.07
    件äºĭ
    -0.07
    asil
    -0.07
    adel
    -0.07
    POSITIVE LOGITS
    éĥ½ä¸įæķ¢
    0.11
     obliv
    0.11
    ç¬Ķè®°æľ¬
    0.11
    åĨħåŃĺ
    0.10
    catch
    0.10
    彪
    0.10
    éĩijåŃĹ
    0.10
    缴æĴŃéĹ´
    0.09
    èĩªå·±çļĦ
    0.09
    å¤ĩæĪĺ
    0.09
    Activations Density 0.137%

    No Known Activations