© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2267
    Prev
    Next
    INDEX
    Explanations

    bio-, bio-engineering, bio-sciences

    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
     Dangerous
    -0.18
    Ħ
    -0.18
    ŀ
    -0.18
    建çŃijçī©
    -0.18
    OrCreate
    -0.18
    birthday
    -0.18
     bleak
    -0.17
     demeanor
    -0.17
    BigInteger
    -0.17
     NEO
    -0.17
    POSITIVE LOGITS
    åŃ¦å®¶
    0.34
    /ec
    0.30
    istic
    0.24
     sciences
    0.23
    aceous
    0.23
    /math
    0.22
    asses
    0.21
    fon
    0.21
    se
    0.20
    /engine
    0.20
    Activations Density 0.085%

    No Known Activations