© 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. 22217
    Prev
    Next
    INDEX
    Explanations

    zero

    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
    -0.06
     relatively
    -0.05
    åľ¨æѤ
    -0.05
     general
    -0.05
    un
    -0.05
    空çĻ½
    -0.05
    instead
    -0.05
     random
    -0.05
    akil
    -0.05
    _blank
    -0.04
    POSITIVE LOGITS
     swear
    0.07
    gó
    0.07
    hini
    0.07
    åĨįæľī
    0.07
    dent
    0.07
     reprises
    0.07
    bjerg
    0.06
    /native
    0.06
    -go
    0.06
     огон
    0.06
    Activations Density 0.051%

    No Known Activations