© 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. 19976
    Prev
    Next
    INDEX
    Explanations

    long hair

    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
     Extr
    -0.05
     extr
    -0.05
    åħ¶äºĮ
    -0.05
    untu
    -0.05
    æĿ¡æĿ¡
    -0.05
    MV
    -0.05
    enda
    -0.05
    atal
    -0.05
     Temporary
    -0.05
    åĴĮçī¹çĤ¹
    -0.05
    POSITIVE LOGITS
    éĿ©
    0.07
    zeÅĽ
    0.06
    èĭį
    0.06
    åį«
    0.06
    èĩ³åħ³
    0.06
    анÑĤи
    0.06
    antis
    0.06
    æ²Į
    0.06
    ieber
    0.06
    onaut
    0.06
    Activations Density 0.004%

    No Known Activations