© 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. 22-TRANSCODER-HP
    7. 112021
    Prev
    Next
    INDEX
    Explanations

    Regional/National

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ýt
    -0.28
    aptic
    -0.28
    ismic
    -0.27
     down
    -0.26
    down
    -0.25
    æ´Ĺ
    -0.25
    åIJĮåŁİ
    -0.24
    ipsis
    -0.24
    akra
    -0.24
    Ñıд
    -0.24
    POSITIVE LOGITS
    ensi
    0.29
    åı¦ä¸Ģè¾¹
    0.26
    zure
    0.25
    ense
    0.25
    lund
    0.25
    _KEYWORD
    0.25
    é«ĺçŃī
    0.25
     tolerate
    0.24
     bait
    0.24
     acute
    0.24
    Activations Density 0.006%

    No Known Activations