© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51563
    Prev
    Next
    INDEX
    Explanations

    felony murder rule

    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
    ATES
    -0.09
    éĤ»å±ħ
    -0.08
    èŀ³
    -0.08
    dur
    -0.08
    çħ³
    -0.08
    oster
    -0.08
    Sweden
    -0.08
    æĸij
    -0.08
     اÙĦÙħتØŃ
    -0.08
    APPED
    -0.08
    POSITIVE LOGITS
    .linkedin
    0.09
    å®ŀæĸ½ç»ĨåĪĻ
    0.09
    .prevent
    0.09
    akash
    0.08
    åĴĮæĬĢæľ¯
    0.08
    sdk
    0.08
    工信éĥ¨
    0.08
    æĸĩæĺİåŁİå¸Ĥ
    0.08
    ajan
    0.08
    çĸ«æĥħå½±åĵį
    0.08
    Activations Density 0.756%

    No Known Activations