© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1772
    Prev
    Next
    INDEX
    Explanations

    file extensions like jpg, mov, txt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    对åħ¬åı¸
    -0.23
    gé
    -0.23
    ç»ĪçĶŁ
    -0.23
     secrets
    -0.23
    ÑģÑĤвÑĥ
    -0.23
    JD
    -0.22
    _ITEMS
    -0.22
    _fatal
    -0.22
    伸åĩº
    -0.22
    CTR
    -0.22
    POSITIVE LOGITS
     Exterior
    0.24
     Recovery
    0.24
    çŃīåIJĦç§į
    0.24
     Tactical
    0.23
    redd
    0.23
     Outer
    0.23
    reff
    0.23
    亲
    0.23
     Remarks
    0.23
     COPYING
    0.23
    Activations Density 0.006%

    No Known Activations