© 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. 17350
    Prev
    Next
    INDEX
    Explanations

    measuring or detecting information

    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
    kens
    -0.06
    ukke
    -0.06
    è²ī
    -0.05
    åĮĸå¤ĦçIJĨ
    -0.05
    úm
    -0.05
     harap
    -0.05
    probe
    -0.05
    luv
    -0.05
    åĮĸ管çIJĨ
    -0.05
    ickers
    -0.05
    POSITIVE LOGITS
    è¶Ĭæĺ¯
    0.06
    inous
    0.06
    -he
    0.05
    æµ·æ´ĭ
    0.05
    ä¸ĢçĤ¹ä¸Ģæ»´
    0.05
    缺çĤ¹æĺ¯
    0.05
     fulfilling
    0.05
    ä»ĺ
    0.05
    trail
    0.05
    å°±è¶Ĭ
    0.05
    Activations Density 0.014%

    No Known Activations