© 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. 39656
    Prev
    Next
    INDEX
    Explanations

    championships and bowls

    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
    èĵŁ
    -0.10
    agine
    -0.09
    çıı
    -0.09
    åĽºå®ļçļĦ
    -0.09
    å°ıåŃIJ
    -0.09
    æŃ¤äºº
    -0.09
    åľ°ä¸Ń
    -0.08
    天æīį
    -0.08
    ç¿İ
    -0.08
    ä¼ģä¸ļåıijå±ķ
    -0.08
    POSITIVE LOGITS
    .failure
    0.10
    toa
    0.10
    çĭ®åŃIJ
    0.09
    Attached
    0.08
    roma
    0.08
     sadd
    0.08
    æłĩå¿Ĺ
    0.08
    èĥľåĪ©
    0.08
    Abb
    0.08
    TEAM
    0.08
    Activations Density 0.039%

    No Known Activations