© 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. 18772
    Prev
    Next
    INDEX
    Explanations

    crush, squash, knock out

    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
    auber
    -0.06
    deg
    -0.06
     *\
    -0.06
     :\
    -0.06
    rans
    -0.06
    èªĵ
    -0.06
    çĶ¨æ³ķ
    -0.05
    rig
    -0.05
    çĬĢ
    -0.05
    amac
    -0.05
    POSITIVE LOGITS
    æ¾İ
    0.06
    dad
    0.06
     ë
    0.06
    erei
    0.06
     Overnight
    0.06
     Ñģвид
    0.06
    kki
    0.05
    ariah
    0.05
    eur
    0.05
    SED
    0.05
    Activations Density 0.001%

    No Known Activations