© 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. 25149
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    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
    é»İæĺİ
    -0.31
    gui
    -0.27
    éĴ³
    -0.26
    fce
    -0.25
    ä¹Łä¸įè¦ģ
    -0.25
     MCS
    -0.25
    ä¸ĢæŃ¥
    -0.25
     ivory
    -0.25
    justice
    -0.25
    交åıī
    -0.25
    POSITIVE LOGITS
     NotImplemented
    0.27
     admitting
    0.27
    Ĭ¶æĢģ
    0.25
    olem
    0.24
    åŁł
    0.24
    olic
    0.24
    emode
    0.24
    loff
    0.24
    oles
    0.23
    ç»ĵæŀľæĺ¾ç¤º
    0.23
    Activations Density 0.006%

    No Known Activations