© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16655
    Prev
    Next
    INDEX
    Explanations

    lie at/in/within

    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
    Negative Logits
    راس
    -0.10
    åĴĮåľ°åĮº
    -0.09
    idad
    -0.09
    ihu
    -0.09
    igu
    -0.09
    cai
    -0.09
    иÑħ
    -0.09
    /Linux
    -0.09
    era
    -0.08
    å£ħ
    -0.08
    POSITIVE LOGITS
    æ±Łå±±
    0.10
    /is
    0.10
     dormant
    0.09
    ahl
    0.09
    åīįåı°
    0.09
    uries
    0.09
    çĶ¸
    0.09
    erval
    0.08
    rams
    0.08
    ings
    0.08
    Activations Density 0.032%

    No Known Activations