© 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. 23018
    Prev
    Next
    INDEX
    Explanations

    shipping costs and delivery options

    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
    åĴĸ
    -0.09
    åľ¨å¸Ĥåľºä¸Ĭ
    -0.08
    æį®æĬ¥éģĵ
    -0.08
    è¤Ĭ
    -0.08
    .intent
    -0.08
    榨
    -0.08
    _orientation
    -0.07
    _REPLY
    -0.07
    修补
    -0.07
    为人
    -0.07
    POSITIVE LOGITS
    è¿IJè´¹
    0.10
    éħįéĢģ
    0.10
    ç½ijçĤ¹
    0.09
    干线
    0.09
    ç¿Ĭ
    0.08
    åģļä¸įåĪ°
    0.08
     frag
    0.08
    AMPLE
    0.08
    å°Ĭ
    0.08
    大å®Ĺ
    0.08
    Activations Density 0.059%

    No Known Activations