© 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. 2383
    Prev
    Next
    INDEX
    Explanations

    cross over or paths

    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
    edy
    -0.10
    æ¡Ħ
    -0.10
    æĽ´å¤ļ精彩
    -0.10
    afone
    -0.10
    åĩŃ
    -0.10
    åħ¬åħ±åį«çĶŁ
    -0.10
    à¸Ħà¸ĵะ
    -0.10
    inges
    -0.10
    erule
    -0.10
    ä¸Ģå¥Ĺ
    -0.09
    POSITIVE LOGITS
     crossed
    0.09
    èľĢ
    0.08
     crossing
    0.08
    æ¾¹
    0.08
     centr
    0.08
    åįģåŃĹ
    0.08
    .assertIsInstance
    0.08
    cross
    0.07
     recap
    0.07
     cross
    0.07
    Activations Density 0.014%

    No Known Activations