© 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. 9572
    Prev
    Next
    INDEX
    Explanations

    musicians and actors

    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
    erk
    -0.10
    çĹĽ
    -0.09
    Ñģим
    -0.09
     Hank
    -0.09
    åĴĮåıijå±ķ
    -0.09
     harm
    -0.08
    çľ¼çľĭ
    -0.08
    çķª
    -0.08
    å©
    -0.08
    çĸ²æĥ«
    -0.08
    POSITIVE LOGITS
    åħ¬åħ±åľºæīĢ
    0.11
    åį°ç«ł
    0.10
    åĩĿ
    0.10
    åŁ¹
    0.10
    驱
    0.10
    éĴ§
    0.10
    çĥ§çĥ¤
    0.09
    èģĮä¸ļéģĵå¾·
    0.09
    çĥĺ
    0.09
    éķ¿åŁİ
    0.09
    Activations Density 0.040%

    No Known Activations