© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 755
    Prev
    Next
    INDEX
    Explanations

    organic, savory, and other descriptors

    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
    rozen
    -0.25
    容éĩı
    -0.21
    yr
    -0.21
    onus
    -0.21
    ħ§
    -0.21
    rax
    -0.21
     tá»Ļi
    -0.20
    -holder
    -0.20
    obl
    -0.20
    INATION
    -0.20
    POSITIVE LOGITS
    soup
    0.24
    çĤĿ
    0.23
    éĿĴéĵľ
    0.22
     side
    0.21
    eut
    0.21
     plate
    0.21
    -kind
    0.20
    uron
    0.20
     yet
    0.20
     Veg
    0.20
    Activations Density 0.004%

    No Known Activations