© 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. 717
    Prev
    Next
    INDEX
    Explanations

    option for or to

    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
    abouts
    -0.19
    -formed
    -0.18
    UNS
    -0.18
    èĪªéģĵ
    -0.18
    OWN
    -0.17
    OCI
    -0.17
    Assignable
    -0.17
     havoc
    -0.17
    pes
    -0.17
    IELD
    -0.17
    POSITIVE LOGITS
    portunity
    0.23
    entially
    0.23
    ality
    0.23
    nel
    0.22
    ally
    0.22
    eer
    0.22
    getter
    0.21
    lessly
    0.21
    ential
    0.20
    ário
    0.20
    Activations Density 0.049%

    No Known Activations