© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52122
    Prev
    Next
    INDEX
    Explanations

    memory and its related terms

    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
    swith
    -0.09
    sWith
    -0.09
    ðŁı»
    -0.09
    èµĸ以
    -0.08
     Lew
    -0.08
    åĽ½äºº
    -0.08
    odia
    -0.08
    woo
    -0.08
    etty
    -0.08
    обоÑĢ
    -0.08
    POSITIVE LOGITS
    onda
    0.11
    æ·±å¤Ħ
    0.10
    phis
    0.10
    çĬ¶åĨµ
    0.09
    washer
    0.08
    æıŃ
    0.08
    asto
    0.08
    ders
    0.08
    -efficient
    0.08
    fly
    0.08
    Activations Density 0.050%

    No Known Activations