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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161840
    Prev
    Next
    INDEX
    Explanations

    Roles and Occupations

    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
    åħĪè¡Į
    -0.28
    æĴŃåĩº
    -0.27
    åѵåĮĸåĻ¨
    -0.26
    æľīå¾Ī大çļĦ
    -0.26
    \Context
    -0.25
    è¾ħåĬ©
    -0.25
    istani
    -0.24
    ä¸ĢäºĽ
    -0.24
     indifference
    -0.24
    çīº
    -0.24
    POSITIVE LOGITS
     Du
    0.26
    ging
    0.25
    GING
    0.25
     iota
    0.24
    æ¤ħ
    0.24
    ä¸įå¾Ĺå·²
    0.23
    åĵĹ
    0.23
    åŀ£
    0.23
    _successful
    0.23
    åħ¶éĹ´
    0.22
    Activations Density 0.026%

    No Known Activations