© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5253
    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
    inous
    -0.27
    ç»ĻäºĪäºĨ
    -0.26
    ãĥIJãĥ©ãĥ³ãĤ¹
    -0.26
     mát
    -0.25
    BAL
    -0.24
    è¡Į为
    -0.23
    æºĸ
    -0.23
    她们
    -0.23
    .tt
    -0.23
     Briggs
    -0.23
    POSITIVE LOGITS
    åħ±åIJĮåıijå±ķ
    0.26
    à¥į
    0.26
     sorts
    0.25
    -mail
    0.25
    curr
    0.23
    为人
    0.23
    æݥ触åĪ°
    0.23
     scheduled
    0.23
    éĩįå¤į
    0.23
    artz
    0.23
    Activations Density 0.310%

    No Known Activations