© 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. 8562
    Prev
    Next
    INDEX
    Explanations

    screen or wire and related components

    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
    otts
    -0.09
    NSS
    -0.08
    è·¯ç¨ĭ
    -0.08
    çĩķ
    -0.08
    åŀ©
    -0.08
     Compass
    -0.08
    ä¿¡å¿ĥ
    -0.08
     createStore
    -0.08
    emp
    -0.08
    åĿı
    -0.08
    POSITIVE LOGITS
    dere
    0.10
    æĶ¹è£ħ
    0.09
    å¹ķ
    0.09
    åĪĨ级
    0.09
    orer
    0.09
    ä¸ĵ线
    0.09
    aul
    0.09
    åħ¨å¤©
    0.08
    ä»İä¸Ń
    0.08
    è´²
    0.08
    Activations Density 0.140%

    No Known Activations