© 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. 57290
    Prev
    Next
    INDEX
    Explanations

    coupling property with data

    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
    emption
    -0.09
    èij±
    -0.09
    ì¤Ħ
    -0.09
    å¼ĢæľĹ
    -0.09
    ë£Į
    -0.08
    าà¸Ļ
    -0.08
    磶
    -0.08
    æģļ
    -0.08
    avig
    -0.08
    idual
    -0.08
    POSITIVE LOGITS
    åľ¨ä¸Ģèµ·
    0.11
    ван
    0.11
    reek
    0.11
    TURE
    0.11
    edList
    0.10
    çĪ·
    0.10
    好è¿IJ
    0.10
    stan
    0.10
    以èī²
    0.10
    rons
    0.09
    Activations Density 0.059%

    No Known Activations