© 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. 45387
    Prev
    Next
    INDEX
    Explanations

    closure and relocation

    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
    ëĭ¹
    -0.07
    idou
    -0.07
    acus
    -0.07
     side
    -0.06
    èĩªæķij
    -0.06
     yö
    -0.06
     жаÑĢ
    -0.06
    idon
    -0.06
    istra
    -0.06
    zyd
    -0.06
    POSITIVE LOGITS
    诲
    0.08
    Extensions
    0.08
    á»ħn
    0.08
    åī¤
    0.08
    akk
    0.08
    çĿĢè¿·
    0.08
    ificates
    0.08
    æĹłçĹĩçĬ¶æĦŁæŁĵèĢħ
    0.07
    abbit
    0.07
    迹
    0.07
    Activations Density 0.003%

    No Known Activations