© 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. 18500
    Prev
    Next
    INDEX
    Explanations

    excuse me

    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
    ukk
    -0.07
    accessible
    -0.06
    ANCH
    -0.06
    -than
    -0.06
     interv
    -0.06
    å½Ĵæ¯į
    -0.06
    entiful
    -0.06
    melon
    -0.06
    çľģæŶ
    -0.06
    mailer
    -0.06
    POSITIVE LOGITS
    ect
    0.08
    ects
    0.06
    ama
    0.05
    se
    0.05
    æĸ¹
    0.05
    еÑģÑĤва
    0.05
    atory
    0.05
     hall
    0.05
    ul
    0.05
    ulan
    0.05
    Activations Density 0.002%

    No Known Activations