© 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. 30188
    Prev
    Next
    INDEX
    Explanations

    strategies, utilization, scheme, familiarity

    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
     Fior
    -0.08
    ÙĤÙħ
    -0.08
    arium
    -0.08
    Triple
    -0.08
    iron
    -0.08
    èIJ½åľ°
    -0.08
    é¢Ħå¤ĩ
    -0.07
    onda
    -0.07
     Pre
    -0.07
    eters
    -0.07
    POSITIVE LOGITS
    éĴµ
    0.10
    Ùħد
    0.10
    åİŁåīĩ
    0.09
    åĽ½äºº
    0.09
    马路
    0.09
    çŃĶåį·
    0.09
    èĥ½åĬĽå¼º
    0.09
    çī¯
    0.09
    èĪ¬
    0.09
    毳
    0.09
    Activations Density 0.066%

    No Known Activations