© 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. 34471
    Prev
    Next
    INDEX
    Explanations

    withdraws from

    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
    åĪ°è´¦
    -0.09
    å¹Ħ
    -0.09
    æĥ³è±¡åĬĽ
    -0.09
    olicy
    -0.09
    _Profile
    -0.09
    SnackBar
    -0.09
    æħĪæĤ²
    -0.09
    ioni
    -0.09
    _PADDING
    -0.08
    éļĶå£ģ
    -0.08
    POSITIVE LOGITS
    çĥĪ
    0.10
    è¿ĩå¤ļ
    0.09
     altogether
    0.09
    æľīæ¯Ĵ
    0.09
    为ä¸Ģä½ĵ
    0.09
    追究
    0.09
    å´Ľ
    0.09
    奢
    0.08
    åİŁæľīçļĦ
    0.08
    tim
    0.08
    Activations Density 0.060%

    No Known Activations