© 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. 7939
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
    cient
    -0.24
    æľĢåIJĪéĢĤ
    -0.24
    jid
    -0.24
    _THROW
    -0.24
    ä»ĵ
    -0.24
    *this
    -0.24
     CASCADE
    -0.23
    éĤ£ä¹Īç®Ģåįķ
    -0.23
    _zeros
    -0.23
    raj
    -0.23
    POSITIVE LOGITS
     vs
    0.25
    ãģ§ãģĬ
    0.25
     vont
    0.25
    etus
    0.25
     köz
    0.25
    /epl
    0.25
    ä¸įç¦ģ
    0.24
    fusc
    0.24
    ";}↵
    0.24
    å°¼æĸ¯
    0.23
    Activations Density 0.064%

    No Known Activations