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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8538
    Prev
    Next
    INDEX
    Explanations

    that

    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
    æ¯ıä½į
    -0.26
    çĶ±ä¸ŃåĽ½
    -0.25
    Sn
    -0.25
    .userID
    -0.25
     pass
    -0.24
     incl
    -0.24
    yr
    -0.24
    apiKey
    -0.24
     advising
    -0.24
    apikey
    -0.24
    POSITIVE LOGITS
    转ä¼ļ
    0.26
     HttpHeaders
    0.26
    風
    0.24
    ALL
    0.23
    :convert
    0.23
    æµģåĬ¨
    0.23
     strand
    0.23
     finances
    0.23
    åĬ²
    0.22
     flair
    0.22
    Activations Density 0.323%

    No Known Activations