© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19774
    Prev
    Next
    INDEX
    Explanations

    viagra and visa

    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
    ured
    -0.10
     Ñģек
    -0.10
    izr
    -0.10
    anto
    -0.10
    urate
    -0.10
    chant
    -0.09
    è´¿èµĤ
    -0.09
     Elections
    -0.09
    çĪ·
    -0.09
    Cumhur
    -0.09
    POSITIVE LOGITS
    athi
    0.10
    æĹ¶ä»£
    0.08
    atch
    0.08
    å§IJ妹
    0.08
    aters
    0.07
    ç½ijåıĭè¯Ħ论
    0.07
    0.07
    åĨ³å¿ĥ
    0.07
    ANS
    0.07
    emma
    0.07
    Activations Density 0.002%

    No Known Activations