© 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. 19-TRANSCODER-HP
    7. 8375
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įæŃ»
    -0.24
    nage
    -0.23
    èĩªå·±çļĦ
    -0.23
    yclopedia
    -0.23
     minded
    -0.22
    æĬķèµĦ人
    -0.22
     borne
    -0.22
    adam
    -0.22
    inema
    -0.22
    duct
    -0.22
    POSITIVE LOGITS
    estone
    0.25
    ographically
    0.25
    ±
    0.24
    æݥ触åĪ°
    0.24
    ouched
    0.24
     clickable
    0.24
     touch
    0.23
     sorts
    0.23
    éĹŃ
    0.23
    =num
    0.23
    Activations Density 0.215%

    No Known Activations