© 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. 5566
    Prev
    Next
    INDEX
    Explanations

    TV shows

    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
    è¯ł
    -0.11
    /thumb
    -0.10
    åĤ¨
    -0.10
    ç½²
    -0.10
    è¡ĮåĬ¨è®¡åĪĴ
    -0.09
    äºĪ
    -0.09
    åĬ¨èį¡
    -0.09
    è°
    -0.09
    erture
    -0.09
    æ·¡
    -0.09
    POSITIVE LOGITS
     TV
    0.11
    çĶµè§Ĩ
    0.11
    主æĮģ
    0.10
    综èīºèĬĤ缮
    0.10
     Tv
    0.10
     television
    0.10
    èĬĤ缮
    0.09
     televis
    0.09
    TV
    0.09
    _tv
    0.09
    Activations Density 0.092%

    No Known Activations