© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19794
    Prev
    Next
    INDEX
    Explanations

    describing negative actions or characters

    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
    åĸĦ
    -0.05
     gracefully
    -0.05
     solo
    -0.05
    åģ¶
    -0.05
    åĸĦæĦı
    -0.05
    éĺµ
    -0.05
    opa
    -0.05
    osa
    -0.05
    个
    -0.05
    os
    -0.05
    POSITIVE LOGITS
     оÑĤÑĤ
    0.07
    engan
    0.07
    [:]
    0.06
    еÑĢна
    0.06
    omination
    0.06
    åĩ¶çĮĽ
    0.06
     اÙĦÙħØŃاÙģظ
    0.06
    èĥ§
    0.06
    ØŃات
    0.06
    ché
    0.06
    Activations Density 0.054%

    No Known Activations