© 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. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89749
    Prev
    Next
    INDEX
    Explanations

    contact lenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä½ľåĿĬ
    -0.28
    [-
    -0.27
     bet
    -0.26
    å°Ĭ
    -0.26
    åıįæĺł
    -0.25
     Interpret
    -0.25
    éĩįè§Ĩ
    -0.25
    丸
    -0.25
    defined
    -0.25
    滥çĶ¨
    -0.25
    POSITIVE LOGITS
    泺
    0.28
    zza
    0.27
    orda
    0.26
    vida
    0.26
    ayne
    0.26
    uchsia
    0.25
    pNet
    0.25
    chine
    0.25
    utta
    0.25
    ırl
    0.24
    Activations Density 3.858%

    No Known Activations