© 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. 20608
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and numbers

    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
    ivot
    -0.06
    écu
    -0.06
    åıĹä¼Ĺ
    -0.06
    éĹ®åıĬ
    -0.06
    altar
    -0.06
    è¹Ī
    -0.06
    äºļäºİ
    -0.06
    åıijçĶŁæŶ
    -0.06
    ullah
    -0.06
    åıĹæķĻèĤ²
    -0.06
    POSITIVE LOGITS
    oncini
    0.05
    sau
    0.05
     safely
    0.05
    å®ŀæķĪ
    0.05
    rew
    0.05
    saf
    0.05
     fiction
    0.05
    wr
    0.04
    vlo
    0.04
    æĴ¤åĽŀ
    0.04
    Activations Density 0.001%

    No Known Activations