© 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. 31716
    Prev
    Next
    INDEX
    Explanations

    top [followed by noun]

    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
    æĩĭ
    -0.09
    STACK
    -0.09
    trash
    -0.09
     Andres
    -0.09
    atre
    -0.09
    MATRIX
    -0.09
     trá»Ŀi
    -0.09
    InitStruct
    -0.08
    _MAC
    -0.08
    æĢ§çĸ¾çĹħ
    -0.08
    POSITIVE LOGITS
    variants
    0.09
    ÑĢаÐ
    0.09
    å°±èĥ½å¤Ł
    0.08
    åİŁåħĪ
    0.08
    alt
    0.08
    roph
    0.08
    zie
    0.08
    urf
    0.08
    çĸĨ
    0.08
    西æĸ¹
    0.08
    Activations Density 0.017%

    No Known Activations