© 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. 61465
    Prev
    Next
    INDEX
    Explanations

    rooms in a house

    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
    éĢīåĿĢ
    -0.10
     Ship
    -0.09
    ìī¬
    -0.09
    æħ°
    -0.09
    éĢłèĪ¹
    -0.08
    Intern
    -0.08
    纨
    -0.08
     GeliÅŁ
    -0.08
     Intern
    -0.08
    å¡«è¡¥
    -0.08
    POSITIVE LOGITS
    客åİħ
    0.16
    åį§å®¤
    0.16
    åľ¨å®¶éĩĮ
    0.13
    家ä¸Ń
    0.13
    书æĪ¿
    0.13
    家å±ħ
    0.13
    åݨæĪ¿
    0.12
    家çĶ¨
    0.12
     kitchen
    0.12
     household
    0.12
    Activations Density 0.079%

    No Known Activations