© 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. 6494
    Prev
    Next
    INDEX
    Explanations

    an

    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
    æīĭæĮģ
    -0.29
    åıijå±ķéĺ¶æ®µ
    -0.27
    WindowState
    -0.27
     plag
    -0.26
     permitted
    -0.25
    ATAR
    -0.25
    held
    -0.25
    atar
    -0.24
    heard
    -0.24
     limite
    -0.24
    POSITIVE LOGITS
    count
    0.32
     equivalent
    0.32
     baÅŁÄ±na
    0.31
     equivalents
    0.30
    缸å½ĵäºİ
    0.30
     amount
    0.29
     Equivalent
    0.29
    äºĨå¤ļå°ij
    0.29
    cum
    0.28
    积累
    0.28
    Activations Density 0.034%

    No Known Activations