© 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. 5245
    Prev
    Next
    INDEX
    Explanations

    Scraped/unrelated text snippets

    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
    éĵ¾
    -0.28
    éıĪ
    -0.26
     force
    -0.25
    temps
    -0.25
    åIJĮç±»
    -0.25
     easiest
    -0.24
     FORCE
    -0.24
    :\"
    -0.24
     retrie
    -0.24
     stocks
    -0.24
    POSITIVE LOGITS
    对å¤ĸ
    0.28
    -details
    0.28
    umba
    0.27
    çĿ¦
    0.26
    gien
    0.25
    metics
    0.24
    åĵķ
    0.24
    ä¸İåIJ¦
    0.24
    ught
    0.24
     иÑģп
    0.24
    Activations Density 0.013%

    No Known Activations