© 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. 2526
    Prev
    Next
    INDEX
    Explanations

    malformation, ischemia

    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
     Hole
    -0.24
    åĸĿèĮ¶
    -0.23
    -sign
    -0.22
    麾
    -0.22
    _bus
    -0.22
    qual
    -0.22
    å¥Ĺè·¯
    -0.21
    tsy
    -0.20
    FromClass
    -0.20
     photon
    -0.20
    POSITIVE LOGITS
     INLINE
    0.23
     discharge
    0.22
     getService
    0.22
    廪
    0.22
     comprom
    0.21
     provid
    0.21
     discharged
    0.21
    roid
    0.21
    noinspection
    0.21
     ([]
    0.21
    Activations Density 0.002%

    No Known Activations