© 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. 36347
    Prev
    Next
    INDEX
    Explanations

    virtual memory and memory size

    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
    æ¤Ĵ
    -0.10
    scoped
    -0.09
     Bren
    -0.09
    Jam
    -0.09
    æĥħä¾£
    -0.09
    å±Ĥåĩº
    -0.09
    æĥ³åİ»
    -0.09
    .drawer
    -0.08
    建çŃijå¸Ī
    -0.08
    æ¯ķ
    -0.08
    POSITIVE LOGITS
    åĨħåŃĺ
    0.15
     memory
    0.13
    memory
    0.13
    空éĹ´
    0.11
    ä½Ķ
    0.11
    Memory
    0.11
     space
    0.10
    è¿Ļéĥ¨åĪĨ
    0.10
     ê³µê°Ħ
    0.10
    emory
    0.10
    Activations Density 0.248%

    No Known Activations