© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37521
    Prev
    Next
    INDEX
    Explanations

    vehicle accessories and modification

    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
    绿èī²
    -0.09
     Dump
    -0.09
    åİĨåı²æĸ°
    -0.08
    ulton
    -0.08
    å¸Ļ
    -0.08
     reint
    -0.08
    Dump
    -0.08
    fullname
    -0.08
    è·º
    -0.08
    åħ¨çIJĥåĮĸ
    -0.08
    POSITIVE LOGITS
    åĽ¢
    0.12
    èĩ§
    0.10
    çĶ¨è½¦
    0.10
     diy
    0.09
    èļ©
    0.09
    åľĺ
    0.09
    çī²
    0.09
    ç¤¾åĽ¢
    0.09
    atal
    0.09
    avage
    0.09
    Activations Density 0.125%

    No Known Activations