© 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. 33350
    Prev
    Next
    INDEX
    Explanations

    voices heard

    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
    æİ¢
    -0.10
    嵬
    -0.09
     narrowly
    -0.09
    ory
    -0.08
    obil
    -0.08
     testing
    -0.08
    æĬ±
    -0.08
    åĭ¾
    -0.08
    åĦĴ
    -0.08
     Mobil
    -0.08
    POSITIVE LOGITS
    å£°éŁ³
    0.25
     voices
    0.23
     voice
    0.23
    çļĦå£°éŁ³
    0.23
    èģ²éŁ³
    0.20
    åıij声
    0.20
     голоÑģ
    0.18
     Voices
    0.18
     voz
    0.18
    ä¹ĭ声
    0.18
    Activations Density 0.078%

    No Known Activations