© 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. 18308
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    assy
    -0.06
    akedown
    -0.06
    ubi
    -0.06
    å±ķçİ°åĩºäºĨ
    -0.06
    à¹Ĥà¸Ń
    -0.06
    ahasa
    -0.06
    ñez
    -0.06
    DidAppear
    -0.06
    пада
    -0.05
    mack
    -0.05
    POSITIVE LOGITS
    ight
    0.06
    cur
    0.06
    åIJįåŃĹ
    0.05
    Names
    0.05
    ourn
    0.05
    çĶľ
    0.05
    æĽ²
    0.05
    иÑĤÑĮ
    0.05
    çĶ¨äºİ
    0.05
     xạ
    0.05
    Activations Density 0.001%

    No Known Activations