© 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
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 192
    Prev
    Next
    INDEX
    Explanations

    contact information

    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
    .tight
    -0.24
    ounter
    -0.22
    CompatActivity
    -0.22
     paired
    -0.21
    _CIPHER
    -0.21
    Foreground
    -0.21
    åĬ£
    -0.21
    Analy
    -0.21
    _into
    -0.21
    lopedia
    -0.21
    POSITIVE LOGITS
    éĤ®ç®±
    0.41
     contact
    0.39
     email
    0.34
     CONTACT
    0.32
     contacted
    0.31
    çĶµè¯Ŀ
    0.31
    åĪĨ管
    0.31
     Contact
    0.31
    contact
    0.31
    .contact
    0.31
    Activations Density 0.021%

    No Known Activations