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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4713
    Prev
    Next
    INDEX
    Explanations

    inc

    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
    âĢĸ
    -0.27
    带åĪ°
    -0.27
     Highlands
    -0.26
    çĶ¨åĬĽ
    -0.26
     AFC
    -0.26
    rag
    -0.25
    lor
    -0.25
     indifferent
    -0.25
    追究
    -0.25
    æ·±åİļ
    -0.24
    POSITIVE LOGITS
    elia
    0.26
    åľ¨åĵªéĩĮ
    0.25
    iao
    0.25
    опеÑĢ
    0.24
    sey
    0.24
    æĨ¶
    0.24
    åľ¨å¤ĸéĿ¢
    0.24
    lettes
    0.24
     Gew
    0.23
    .less
    0.23
    Activations Density 0.016%

    No Known Activations