© 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. 4754
    Prev
    Next
    INDEX
    Explanations

    adjectives

    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
    åľ¨è·¯ä¸Ĭ
    -0.28
    coma
    -0.26
    holm
    -0.25
    ODO
    -0.25
    yr
    -0.25
    çİĩè¾¾åĪ°
    -0.25
    -makers
    -0.24
    -pr
    -0.24
    od
    -0.24
    æłĩåĩĨåĮĸ
    -0.24
    POSITIVE LOGITS
     given
    0.29
     none
    0.28
    iese
    0.26
     sharp
    0.26
     modeling
    0.26
    given
    0.26
    bose
    0.25
     modelling
    0.25
     tight
    0.24
     subt
    0.24
    Activations Density 0.123%

    No Known Activations