© 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. 18978
    Prev
    Next
    INDEX
    Explanations

    industry

    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
    ç»ı
    -0.06
    éĹĬ
    -0.05
    广åijĬæľįåĬ¡
    -0.05
    容
    -0.05
    reck
    -0.05
    cich
    -0.05
    mental
    -0.05
    swer
    -0.05
     butuhkan
    -0.05
    UCE
    -0.05
    POSITIVE LOGITS
    æ°ı
    0.06
    agent
    0.06
     literally
    0.05
    anela
    0.05
    çŃīåįķä½į
    0.05
    çĶļèĩ³æ¯Ķ
    0.05
    ianas
    0.05
    åīĤçŃī
    0.05
     literal
    0.05
    ัà¸į
    0.05
    Activations Density 0.008%

    No Known Activations