© 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. 33045
    Prev
    Next
    INDEX
    Explanations

    cases and investigations

    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
    åĬ²
    -0.10
    åŁ¹è®ŃæľºæŀĦ
    -0.10
    è¿ĻæĶ¯
    -0.10
    æijŃ
    -0.09
    ç»ĻåŃ©åŃIJ
    -0.09
    thew
    -0.09
    çªij
    -0.09
    ä½łåĸľæ¬¢
    -0.09
    å¿į
    -0.08
    é¡¿
    -0.08
    POSITIVE LOGITS
    æ¡Ī件
    0.24
     cases
    0.21
    æ¡ĪåŃIJ
    0.20
    cases
    0.18
     Cases
    0.17
     casos
    0.16
     case
    0.16
    ãĤ±ãĥ¼ãĤ¹
    0.15
    case
    0.15
    æ¡Īä¾ĭ
    0.15
    Activations Density 0.407%

    No Known Activations