© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32402
    Prev
    Next
    INDEX
    Explanations

    output filters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ạ
    -0.09
    æīĵçģ«
    -0.08
    zyw
    -0.08
    å°Ķå¾·
    -0.08
    ç»ıæµİåľĪ
    -0.08
    ÑĢиан
    -0.07
    åħ¨éĥ¨è¯Ħ论
    -0.07
    éĺ»çĩĥ
    -0.07
    ç¯Ŀ
    -0.07
    èŀį
    -0.07
    POSITIVE LOGITS
     outputs
    0.10
     response
    0.10
     Response
    0.10
    -output
    0.09
     output
    0.09
    output
    0.09
     causal
    0.09
    Response
    0.09
     processes
    0.09
    è¾ĵåĩº
    0.09
    Activations Density 0.036%

    No Known Activations