© 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. 2726
    Prev
    Next
    INDEX
    Explanations

    correctional facility

    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
    -0.26
    çİ°åŃĺ
    -0.23
     gaps
    -0.23
     ÑģовеÑĢÑĪен
    -0.23
     existing
    -0.23
    sut
    -0.22
    izu
    -0.22
    sst
    -0.22
    s
    -0.21
    缺åı£
    -0.21
    POSITIVE LOGITS
    nan
    0.21
    éĺ²çĽĹ
    0.21
     vX
    0.21
    tran
    0.21
    park
    0.21
     assurances
    0.20
    ä½İ温
    0.20
    berry
    0.20
    èª
    0.20
    èı°
    0.20
    Activations Density 0.007%

    No Known Activations