© 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. 27827
    Prev
    Next
    INDEX
    Explanations

    mineral

    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
    ãģ¶ãĤĬ
    -0.10
    pper
    -0.10
    ðŁı»
    -0.09
    opher
    -0.09
    á»ĵn
    -0.09
    é»İæĺİ
    -0.09
    ote
    -0.09
    åĴĮåľ°åĮº
    -0.08
    æ¸ħæĻ¨
    -0.08
    è¿Ļ对äºİ
    -0.08
    POSITIVE LOGITS
    ized
    0.14
    ization
    0.12
    ogy
    0.10
    izing
    0.10
    ised
    0.10
    izer
    0.10
    ials
    0.09
    ising
    0.09
    isation
    0.09
    isateur
    0.09
    Activations Density 0.010%

    No Known Activations