© 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. 17954
    Prev
    Next
    INDEX
    Explanations

    fail to / fail over

    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
    /from
    -0.10
    ree
    -0.09
    illery
    -0.08
    rid
    -0.08
    dash
    -0.08
    ÑıÑģн
    -0.08
    VELO
    -0.08
     пÑĢоиÑģ
    -0.08
    åºŁå¼ĥ
    -0.08
    ehler
    -0.08
    POSITIVE LOGITS
    fully
    0.12
    ures
    0.11
    leur
    0.11
    计è¾ĥ
    0.10
    ocab
    0.09
    over
    0.09
    ulent
    0.09
    åµİ
    0.09
     miser
    0.09
    /errors
    0.09
    Activations Density 0.041%

    No Known Activations