© 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. 22820
    Prev
    Next
    INDEX
    Explanations

    mass and religious services

    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
    è°Ĺ
    -0.10
    éļĻ
    -0.09
    ä¹Łç®Ĺ
    -0.09
    éļıæīĭ
    -0.08
    æ³³
    -0.08
    çĶĦ
    -0.08
    å®®
    -0.08
    èĩªå¾ĭ
    -0.08
    owie
    -0.08
    ç»ĨåĪĨ
    -0.08
    POSITIVE LOGITS
    ius
    0.09
    åľŁåľ°
    0.09
    çĶ«
    0.09
    è§ĦèĮĥ
    0.09
    izin
    0.09
    CHANT
    0.09
    bourg
    0.08
    chants
    0.08
    Implemented
    0.08
    æĻ®
    0.08
    Activations Density 0.037%

    No Known Activations