© 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. 5799
    Prev
    Next
    INDEX
    Explanations

    suffocation, smell, outbeck, is (-

    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
    æĬĺ
    -0.10
    éŨå¤ĸ
    -0.10
    çļĦä¸ľè¥¿
    -0.08
    IAS
    -0.08
    åĢĴ
    -0.08
    isa
    -0.08
    fel
    -0.08
    æ¬Ĭ
    -0.08
    è¤Ĵ
    -0.08
    æĿĥ
    -0.08
    POSITIVE LOGITS
    åģİ
    0.12
    æŀķ
    0.11
    ç´§å¯Ĩ
    0.10
    èĤĵ
    0.10
    亲çĪ±
    0.10
    éŁ³
    0.10
    äºĴè¡¥
    0.10
    åģľçķĻåľ¨
    0.09
    èı½
    0.09
    è£ģåijĺ
    0.09
    Activations Density 0.014%

    No Known Activations