© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19481
    Prev
    Next
    INDEX
    Explanations

    daylight hours and exposure

    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
    ä¹İ
    -0.10
    çijĻ
    -0.09
    æĪijåıijçİ°
    -0.09
    ãĢħ
    -0.09
    åħ¶å®ĥéĹ®é¢ĺ
    -0.09
    ðŁı»
    -0.09
    OrFail
    -0.09
    è¦ģçŁ¥éģĵ
    -0.09
    italic
    -0.09
    esan
    -0.08
    POSITIVE LOGITS
    ted
    0.13
    ty
    0.10
    ten
    0.10
    ites
    0.09
    ton
    0.09
    ÑĤай
    0.08
    ated
    0.08
    ued
    0.08
    åį¿
    0.08
    æ·±å¤Ħ
    0.08
    Activations Density 0.007%

    No Known Activations