© 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. 34077
    Prev
    Next
    INDEX
    Explanations

    negative sentiment

    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
    ä¸įæħİ
    -0.09
    æĺĿ
    -0.09
    æļijåģĩ
    -0.09
    yers
    -0.09
    CESS
    -0.08
    æŀľæ±ģ
    -0.08
    mma
    -0.08
    áºŃn
    -0.08
     Assass
    -0.08
    aders
    -0.08
    POSITIVE LOGITS
    oure
    0.10
    å¦Ħ
    0.09
    å¾ģ
    0.08
    heck
    0.08
    ØŃÙĪ
    0.08
     heck
    0.08
     sek
    0.08
    é«ĵ
    0.08
    åį«
    0.08
    èijµ
    0.08
    Activations Density 0.029%

    No Known Activations