© 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. 19357
    Prev
    Next
    INDEX
    Explanations

    positive descriptors like thinkers or caring

    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
    ãĥĿãĤ¤ãĥ³ãĥĪ
    -0.06
    ÑģÑĤеÑģÑĤвенно
    -0.05
    ãĥ¼ãĥ³
    -0.05
    orious
    -0.05
    osti
    -0.05
    åħ¬çĽĬäºĭä¸ļ
    -0.05
    ä¸įè°ĥ
    -0.05
     slugg
    -0.05
    ä»Ģ
    -0.05
     Bal
    -0.05
    POSITIVE LOGITS
    elen
    0.06
    arton
    0.06
    akt
    0.06
    éh
    0.06
     micron
    0.05
    ISTER
    0.05
    éĴµ
    0.05
    íݸ
    0.05
    ks
    0.05
    yel
    0.05
    Activations Density 0.213%

    No Known Activations