© 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. 89166
    Prev
    Next
    INDEX
    Explanations

    Forum questions and answers

    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
    aroo
    -0.28
    dy
    -0.27
    æĦŁ
    -0.27
    å®ģ
    -0.25
    abil
    -0.25
    à¤ĸ
    -0.25
    ely
    -0.25
    åĪĨ级
    -0.24
     hero
    -0.24
     below
    -0.24
    POSITIVE LOGITS
    岸
    0.25
    åģļå®Į
    0.23
     Braz
    0.23
    ä¸īçĤ¹
    0.23
     Äijáp
    0.23
    posé
    0.23
    åĴĮæľįåĬ¡
    0.23
     jurisdictions
    0.23
    nez
    0.23
     Barker
    0.23
    Activations Density 27.902%

    No Known Activations