© 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. 948
    Prev
    Next
    INDEX
    Explanations

    Robert [last name]

    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
    tract
    -0.23
    oti
    -0.21
    ä¸įçĦ¶
    -0.21
    lobal
    -0.20
    radient
    -0.20
    tures
    -0.19
    å¤ļãģĦ
    -0.19
     Manit
    -0.18
    ergy
    -0.18
    RATE
    -0.18
    POSITIVE LOGITS
    aceous
    0.32
    eenth
    0.24
    ains
    0.24
    icity
    0.22
    ic
    0.20
    icus
    0.19
    ty
    0.19
    ¤
    0.19
    еÑĨ
    0.19
    ations
    0.18
    Activations Density 0.027%

    No Known Activations