© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21519
    Prev
    Next
    INDEX
    Explanations

    Whereas, opeData, iniBal

    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
    åĴĮåľ°åĮº
    -0.10
    awi
    -0.10
    abouts
    -0.10
    èĩŃ
    -0.10
    nesia
    -0.10
    åĸ·æ¶Ĥ
    -0.09
    äºĨåIJ§
    -0.09
    为æĪij们
    -0.09
    éĴ®
    -0.09
    nett
    -0.08
    POSITIVE LOGITS
    -ser
    0.10
    åľ»
    0.09
    ady
    0.09
    èģĶåIJĪåĽ½
    0.09
    anned
    0.08
    avan
    0.08
    /mac
    0.08
    è°ģèĥ½
    0.08
    tempts
    0.08
    imson
    0.08
    Activations Density 0.001%

    No Known Activations