© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 140
    Prev
    Next
    INDEX
    Explanations

    protein complexes, sequences, structural, translation

    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
    ttp
    -0.23
    cum
    -0.21
    ream
    -0.20
     incomplete
    -0.20
     objections
    -0.20
    ģ
    -0.20
    yt
    -0.20
    ll
    -0.19
    upp
    -0.19
     profitable
    -0.19
    POSITIVE LOGITS
    aceous
    0.44
    ized
    0.32
     calle
    0.25
    åIJįåı«
    0.25
    ially
    0.24
    stalk
    0.24
    /ion
    0.24
    /method
    0.23
    /met
    0.23
    sWith
    0.23
    Activations Density 0.093%

    No Known Activations