© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17219
    Prev
    Next
    INDEX
    Explanations

    look at

    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
    ÑģÑĤо
    -0.05
     برخÙĪردار
    -0.05
     показ
    -0.05
     dispos
    -0.05
    ä¸ĵ家认为
    -0.05
    auc
    -0.05
    yes
    -0.05
     aim
    -0.05
    Ñģой
    -0.05
    å®ĥ以
    -0.05
    POSITIVE LOGITS
    ehler
    0.07
    onia
    0.06
    enk
    0.06
    phe
    0.06
    åļ
    0.06
     Mü
    0.06
    ahanan
    0.06
    isky
    0.06
    Äįe
    0.05
    ÈĽin
    0.05
    Activations Density 0.002%

    No Known Activations