© 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. 23046
    Prev
    Next
    INDEX
    Explanations

    has/have or equipped/support

    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
    ä¸Ģ大åłĨ
    -0.10
    交代
    -0.09
    elyn
    -0.09
    roadcast
    -0.08
    _orient
    -0.08
    estate
    -0.08
    æ¶īåıĬ
    -0.08
    ÑĦан
    -0.08
     QObject
    -0.08
    lier
    -0.08
    POSITIVE LOGITS
    è¿Ļ项
    0.14
    æŃ¤é¡¹
    0.14
    该项
    0.13
    åĬ©çIJĨ
    0.12
     built
    0.10
    built
    0.10
    Built
    0.09
    éļ°
    0.09
    对åħ¶
    0.09
    被åĬ¨
    0.09
    Activations Density 0.259%

    No Known Activations