© 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. 18972
    Prev
    Next
    INDEX
    Explanations

    **The following is the explanation for the neuron's behavior:**Category prefixes

    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
    æ¸Ī
    -0.07
    avor
    -0.06
    æīĢæľª
    -0.06
    æĻ¯
    -0.06
    æī°
    -0.05
    avour
    -0.05
    æĵ¾
    -0.05
    plitude
    -0.05
    ç¥Ńå¥ł
    -0.05
     thao
    -0.05
    POSITIVE LOGITS
    åıĮåĪĽ
    0.06
    çĶ±æѤåı¯è§ģ
    0.06
    icu
    0.05
    bere
    0.05
    缸åħ³è´Łè´£äººè¡¨ç¤º
    0.05
    usen
    0.05
    geg
    0.05
     изÑĭÑģка
    0.05
    atto
    0.05
    kat
    0.05
    Activations Density 0.005%

    No Known Activations