© 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. 18227
    Prev
    Next
    INDEX
    Explanations

    credit limits, guarantees, quota, bond, contracted

    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
    oming
    -0.06
    èĢģ人
    -0.05
    -final
    -0.05
    ÙĪائ
    -0.05
    omet
    -0.05
    çĶ¨å®ĥ
    -0.05
    çĩĥ
    -0.05
    antage
    -0.05
     montage
    -0.05
     compar
    -0.05
    POSITIVE LOGITS
    éĻIJé¢Ŀ
    0.07
    éĶ¥
    0.07
    äºİäºĭ
    0.06
     strength
    0.06
    æ¯įåŃIJ
    0.06
     capacities
    0.06
     sur
    0.06
     gren
    0.06
     inject
    0.06
     strengths
    0.06
    Activations Density 0.007%

    No Known Activations