© 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. 1006
    Prev
    Next
    INDEX
    Explanations

    your needs or requirements

    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
     dürfen
    -0.26
    ilden
    -0.23
    rchive
    -0.22
    巨头
    -0.21
     controlled
    -0.21
    éĻ¤éĿŀ
    -0.21
    INE
    -0.21
    reme
    -0.21
     hypoc
    -0.21
    enburg
    -0.21
    POSITIVE LOGITS
    éľĢæ±Ĥ
    0.40
    åħ·ä½ĵæĥħåĨµ
    0.40
     needs
    0.39
     circumstances
    0.39
     desired
    0.34
    æĥħåĨµ
    0.33
     Needs
    0.32
     conditions
    0.32
     suited
    0.31
     Conditions
    0.30
    Activations Density 0.049%

    No Known Activations