© 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. 49237
    Prev
    Next
    INDEX
    Explanations

    beginning stages

    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
    birds
    -0.09
     increasingly
    -0.09
     typeid
    -0.09
    ç»Ħç»ĩå®ŀæĸ½
    -0.09
    äºĭåħĪ
    -0.09
    ä»Ģä¹ĪæŶåĢĻ
    -0.08
    Ø·ÙĪ
    -0.08
    åĪĽæĸ°åıijå±ķ
    -0.08
    ạm
    -0.08
     каÑĩ
    -0.08
    POSITIVE LOGITS
    çŁ¥åIJį度
    0.10
    led
    0.09
    izers
    0.09
    izr
    0.09
    好æĦŁ
    0.08
    (initial
    0.08
    è¿ĺ以为
    0.08
    iator
    0.08
    æݥ触
    0.08
     stages
    0.08
    Activations Density 0.116%

    No Known Activations