© 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. 48379
    Prev
    Next
    INDEX
    Explanations

    afford, affordable, protection

    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
    åĶ§
    -0.10
    综
    -0.09
    ater
    -0.09
    etric
    -0.09
    룬
    -0.09
    æĥ³æ³ķ
    -0.09
    acho
    -0.09
    orie
    -0.08
    ching
    -0.08
    ugen
    -0.08
    POSITIVE LOGITS
    ably
    0.13
     içerisinde
    0.09
    è¿ĻçĤ¹
    0.09
    åľ¨åĮĹ京
    0.09
    è¦ģ好好
    0.09
    说åĩºæĿ¥
    0.09
    ly
    0.09
    ome
    0.09
    erm
    0.08
    侧ç»ĵæŀĦæĢ§
    0.08
    Activations Density 0.002%

    No Known Activations