© 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. 61251
    Prev
    Next
    INDEX
    Explanations

    memory loss and amnesia

    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
    è£ķ
    -0.12
    è°ĭ
    -0.10
    éļIJéļIJ
    -0.09
     chấp
    -0.09
    okin
    -0.09
    çĵĺ
    -0.09
    _YUV
    -0.09
    èĢ
    -0.09
     acceptable
    -0.09
    ectl
    -0.09
    POSITIVE LOGITS
    MEMORY
    0.11
     memory
    0.11
    /memory
    0.10
    éģĹå¿ĺ
    0.10
    è¨ĺå¾Ĺ
    0.09
    çªį
    0.09
    æ·¦
    0.09
     기ìĸµ
    0.09
    主é¢ĺæ´»åĬ¨
    0.09
    çļĦè®°å¿Ĩ
    0.09
    Activations Density 0.081%

    No Known Activations