© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51704
    Prev
    Next
    INDEX
    Explanations

    numbers preceding "-speed"

    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
    å¿«æį·
    -0.08
    çīµ
    -0.08
    æī«
    -0.08
    ä¸Ńæĸ°
    -0.08
    èŤ
    -0.08
    æ½
    -0.08
     breeze
    -0.07
    å°¸
    -0.07
    axed
    -0.07
    INA
    -0.07
    POSITIVE LOGITS
    æħķ
    0.10
    çĶŁäº§åĴĮ
    0.10
    çıĬçijļ
    0.09
    ç¾İ好çĶŁæ´»
    0.09
    akra
    0.09
    çĴĺ
    0.09
    .removeFrom
    0.09
    idis
    0.08
    .integration
    0.08
    éĥħ
    0.08
    Activations Density 0.026%

    No Known Activations