© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56848
    Prev
    Next
    INDEX
    Explanations

    lin, in, or -ino endings

    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
    à¦ģ
    -0.09
     volna
    -0.09
    er
    -0.09
    ×ķת
    -0.09
    schild
    -0.08
    eenth
    -0.08
    edException
    -0.08
    oenix
    -0.08
    eur
    -0.08
    éĶ¦æ¶Ľ
    -0.08
    POSITIVE LOGITS
    ãĥijãĤ¯ãĥĪ
    0.10
    åijIJ
    0.10
    FINITY
    0.10
    bouw
    0.10
    ners
    0.09
    coln
    0.09
    herited
    0.08
    advert
    0.08
    ãĥĬãĥĥãĥĹ
    0.08
    çĸ²åĬĽ
    0.08
    Activations Density 1.076%

    No Known Activations