© 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. 9252
    Prev
    Next
    INDEX
    Explanations

    requests, attempts, intentions

    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
    itchens
    -0.25
     Protector
    -0.24
     xmin
    -0.24
    europ
    -0.24
    stdClass
    -0.24
    ç½ij讯
    -0.23
    çļĦä¸Ģ项
    -0.23
    een
    -0.23
    edes
    -0.23
    èĤĵ
    -0.23
    POSITIVE LOGITS
    éģ¿åħį
    0.36
    æĸ¹ä¾¿
    0.30
    ç¡®ä¿Ŀ
    0.29
    ä¿Ŀè¯ģ
    0.29
    éĺ²æŃ¢
    0.29
    å®Įæķ´æĢ§
    0.28
     avoid
    0.27
    æĬµå¾¡
    0.26
     ensuring
    0.26
    ä¿Ŀéļľ
    0.26
    Activations Density 0.647%

    No Known Activations