© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17613
    Prev
    Next
    INDEX
    Explanations

    explicit moral, intentions, effects, implications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    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
    ä¾ĭå¦Ĥ
    -0.08
    æ¯Ķå¦Ĥ
    -0.07
     ÐĿапÑĢимеÑĢ
    -0.07
     напÑĢимеÑĢ
    -0.07
    æ¯Ķå¦Ĥ说
    -0.07
    å¦Ĥ对
    -0.06
    напÑĢимеÑĢ
    -0.06
    æŁIJç§į
    -0.06
    ç»Ī身
    -0.06
     daily
    -0.06
    POSITIVE LOGITS
     dissip
    0.06
    bek
    0.06
    tk
    0.06
    CLUDING
    0.06
    äub
    0.05
    IconModule
    0.05
    roz
    0.05
    aln
    0.05
     kemungkinan
    0.05
    ikit
    0.05
    Activations Density 0.004%

    No Known Activations