© 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. 21432
    Prev
    Next
    INDEX
    Explanations

    remove dirt and residues

    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
    anneer
    -0.07
    æŃ¤èµ·å½¼
    -0.07
    å·¾
    -0.07
    æľĿèijĹ
    -0.07
    å±ĬæŶ
    -0.06
     piÄĻk
    -0.06
    ingleton
    -0.06
    ãĥ³ãĥĪãĥ³
    -0.06
    guns
    -0.06
     seuraa
    -0.06
    POSITIVE LOGITS
    ev
    0.05
     bile
    0.05
    oba
    0.05
    å§Ķæīĺ
    0.05
    æ§IJ
    0.05
    带çĿĢ
    0.05
     sign
    0.04
    ep
    0.04
    æ··åIJĪ
    0.04
    sign
    0.04
    Activations Density 0.016%

    No Known Activations