© 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. 2482
    Prev
    Next
    INDEX
    Explanations

    constellations and zodiac signs

    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
    æĬļ
    -0.10
    è¾±
    -0.10
    ocene
    -0.09
    jem
    -0.09
     yat
    -0.09
    ething
    -0.09
    å±Ģ
    -0.08
    éĹº
    -0.08
     prefixed
    -0.08
    emin
    -0.08
    POSITIVE LOGITS
    æĺŁåº§
    0.18
    座
    0.12
     Gemini
    0.10
    çĶŁèĤĸ
    0.10
     constellation
    0.10
     Scor
    0.10
    æľĪ亮
    0.09
    æĺŁè¾°
    0.09
    æĺŁæĺŁ
    0.09
    cÃŃ
    0.09
    Activations Density 0.033%

    No Known Activations