© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6767
    Prev
    Next
    INDEX
    Explanations

    Diverse, unrelated content

    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
    csi
    -0.27
    交åıī
    -0.26
    specific
    -0.25
    mlin
    -0.25
    sense
    -0.24
    eras
    -0.23
    çĶŁåŃĺ
    -0.23
    keit
    -0.23
    PLAY
    -0.23
    .getID
    -0.23
    POSITIVE LOGITS
     upper
    0.28
    upper
    0.27
    ä¸ĬéĻIJ
    0.27
    顾éĹ®
    0.26
     yourselves
    0.26
     Poll
    0.26
     behaviours
    0.26
    åı¦ä¸Ģç§į
    0.26
    æ¦ľ
    0.26
     poll
    0.25
    Activations Density 0.010%

    No Known Activations