© 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. 20402
    Prev
    Next
    INDEX
    Explanations

    names or code keywords

    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
    á»ıi
    -0.06
    ç»ĵæŀľæĺ¾ç¤º
    -0.06
    agro
    -0.06
    éĨ¤
    -0.06
    ãĤĵãģłãģijãģ©
    -0.06
    ÑģÑĤеÑģÑĤвенно
    -0.06
    åĪĥ
    -0.06
    algo
    -0.06
    جز
    -0.06
    ignan
    -0.06
    POSITIVE LOGITS
    hea
    0.06
    оÑı
    0.05
    åĢ¼
    0.05
     elsewhere
    0.05
    æ°ij
    0.05
    è¦Ĩ
    0.05
    kog
    0.05
    é»ĺ
    0.05
    è´µéĩį
    0.05
    ÑĪаÑĤÑĮÑģÑı
    0.05
    Activations Density 0.001%

    No Known Activations