© 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. 57621
    Prev
    Next
    INDEX
    Explanations

    behavior, intention, require, together

    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
    BERS
    -0.10
    ÅŁt
    -0.09
    snd
    -0.09
    য
    -0.09
    ÑıÑģн
    -0.09
    åĬ¨çĶŁæĪIJ
    -0.08
    sı
    -0.08
    ÂŃt
    -0.08
    تع
    -0.08
    éd
    -0.08
    POSITIVE LOGITS
    ../../
    0.34
    ÑģÑı
    0.32
    theless
    0.30
    gether
    0.28
    们
    0.28
    ity
    0.28
    istrator
    0.27
    ly
    0.25
    hip
    0.25
    jourd
    0.24
    Activations Density 2.635%

    No Known Activations