© 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. 20620
    Prev
    Next
    INDEX
    Explanations

    only one species

    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
    /o
    -0.05
    اذ
    -0.05
    强åĪ¶æī§è¡Į
    -0.05
    ivity
    -0.05
    @s
    -0.05
    代
    -0.05
    ship
    -0.05
    æĺ¯ä¸įèĥ½
    -0.04
    als
    -0.04
    å¨ħ
    -0.04
    POSITIVE LOGITS
    ipa
    0.07
    lew
    0.07
    cket
    0.07
    ellini
    0.06
    uhu
    0.06
    ruc
    0.06
    roke
    0.06
    uff
    0.06
     ÑĤака
    0.06
     évolu
    0.06
    Activations Density 0.048%

    No Known Activations