© 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. 27478
    Prev
    Next
    INDEX
    Explanations

    nond-, nons-, antic-, overs- prefixes

    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
    ä¹İ
    -0.12
    pheric
    -0.10
    æĹłç¼Ŀ
    -0.09
    baÅŁÄ±
    -0.09
     ComVisible
    -0.09
    icamente
    -0.08
    tered
    -0.08
    igel
    -0.08
    ially
    -0.08
    ãĥ¡ãĥ³ãĥĪ
    -0.08
    POSITIVE LOGITS
    reme
    0.10
    ent
    0.09
    åĽłä¸ºæĪij们
    0.08
    elon
    0.08
    ources
    0.08
    aval
    0.08
    mission
    0.08
    low
    0.08
    emb
    0.08
    ucc
    0.08
    Activations Density 0.269%

    No Known Activations