© 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. 50249
    Prev
    Next
    INDEX
    Explanations

    until or till

    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
    éķ°
    -0.10
    èķī
    -0.09
    åħĪåIJİ
    -0.09
    _NEG
    -0.09
    eid
    -0.09
    åĨľèµĦ
    -0.08
    æ°¸è¿ľ
    -0.08
    ä»ħæľī
    -0.08
    èĬ¸
    -0.08
     tod
    -0.08
    POSITIVE LOGITS
    ä¸įå½±åĵį
    0.10
     Downing
    0.10
    zel
    0.09
    ä¸ĭæĿ¥çļĦ
    0.09
    ä¹İ
    0.09
    imenti
    0.08
    _ping
    0.08
     depths
    0.08
    æį§
    0.08
    reach
    0.08
    Activations Density 0.089%

    No Known Activations