© 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. 23-TRANSCODER-HP
    7. 24641
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocard
    -0.27
     brings
    -0.26
    ents
    -0.25
    antha
    -0.25
    ocking
    -0.24
    ication
    -0.24
    icism
    -0.24
    edm
    -0.24
    flash
    -0.24
    ä¹Łæĺ¯ä¸Ģç§į
    -0.24
    POSITIVE LOGITS
     foregoing
    0.29
    >((
    0.26
    ”).
    0.26
    çļĦç§ĺå¯Ĩ
    0.25
    éĩĮç¨ĭ
    0.24
    èµĸ以
    0.24
    à¸IJาà¸Ļ
    0.24
    <D
    0.24
    éĻŁ
    0.24
    éĩĮç¨ĭç¢ij
    0.24
    Activations Density 0.019%

    No Known Activations