© 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. 55984
    Prev
    Next
    INDEX
    Explanations

    Charlotte

    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
    ì²ĺ
    -0.10
    çĦ¶æĺ¯
    -0.09
    éĢłæŀĹ
    -0.09
    åĩºå¤Ħ
    -0.09
    ness
    -0.09
    åĴĮå®ĮåĸĦ
    -0.09
    å®īåİ¿
    -0.09
    åıī
    -0.08
    irth
    -0.08
    iners
    -0.08
    POSITIVE LOGITS
    æĽ´å¤ļä¿¡æģ¯
    0.10
    ably
    0.09
     darn
    0.09
    uzzi
    0.09
    ants
    0.09
    enger
    0.09
    à¥įर
    0.08
    é²·
    0.08
    isma
    0.08
    istic
    0.08
    Activations Density 0.010%

    No Known Activations