© 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. 17035
    Prev
    Next
    INDEX
    Explanations

    equation solving with variables

    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
     salat
    -0.05
     populer
    -0.05
    æĥħåĨµåıĬ
    -0.05
    ieri
    -0.05
    äºĭäºĨ
    -0.05
    igli
    -0.05
    anth
    -0.05
    yat
    -0.05
    äºĭçĶ±
    -0.05
     Key
    -0.05
    POSITIVE LOGITS
    inspir
    0.06
     himself
    0.06
    ë³ij
    0.06
     Europas
    0.06
     Himself
    0.05
    ysl
    0.05
    ipe
    0.05
    UTT
    0.05
     recev
    0.05
    ENAME
    0.05
    Activations Density 0.008%

    No Known Activations