© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8853
    Prev
    Next
    INDEX
    Explanations

    utterance and degree

    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
    side
    -0.10
    si
    -0.09
    som
    -0.09
    rb
    -0.09
    _backward
    -0.09
    atic
    -0.09
    rit
    -0.09
    帷
    -0.09
    bei
    -0.09
    san
    -0.08
    POSITIVE LOGITS
    most
    0.13
    IVES
    0.11
    ë§ģ
    0.10
    纯åĩĢ
    0.10
    çļ¿
    0.10
    วา
    0.10
    ment
    0.10
    ances
    0.10
    ties
    0.10
    ials
    0.10
    Activations Density 0.002%

    No Known Activations