© 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. 112534
    Prev
    Next
    INDEX
    Explanations

    Questions and question words

    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
    åĴĮå°ļ
    -0.25
     ÐŁÐ¾ÑĩемÑĥ
    -0.25
    夺åıĸ
    -0.24
    '.↵
    -0.24
    èİ·èĥľ
    -0.24
    subs
    -0.24
    ãģľ
    -0.24
    shal
    -0.23
    vak
    -0.23
     acquired
    -0.23
    POSITIVE LOGITS
     Boyd
    0.26
    -Nov
    0.26
    LU
    0.26
    aroo
    0.25
    æ¶Ĥ
    0.24
    ä¹±
    0.24
    less
    0.24
    械
    0.23
     glBegin
    0.23
    ipur
    0.23
    Activations Density 0.000%

    No Known Activations