© 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. 57606
    Prev
    Next
    INDEX
    Explanations

    hands-on

    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
    sto
    -0.10
    ä¸įä¿¡
    -0.10
    çī¢åĽºæłijç«ĭ
    -0.09
    ä¸Ģéģĵ
    -0.09
    çĽĨåľ°
    -0.09
    istrator
    -0.09
    _ABI
    -0.09
    ãģ¹ãģį
    -0.09
    iversity
    -0.08
    osome
    -0.08
    POSITIVE LOGITS
    ðŁı»
    0.14
    ðŁı¼
    0.11
    ðŁı¾
    0.11
    åĹŁ
    0.11
    ðŁı½
    0.09
    ells
    0.09
    ðŁı¿
    0.09
    elves
    0.09
    hev
    0.09
    anon
    0.09
    Activations Density 0.014%

    No Known Activations