© 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. 112378
    Prev
    Next
    INDEX
    Explanations

    end of sentence

    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
    äºļåĨĽ
    -0.27
    åıĺåİĭ
    -0.26
     accumulate
    -0.25
    èµ·çłģ
    -0.25
     sublist
    -0.25
    积累äºĨ
    -0.25
    _python
    -0.24
    ä¹ŁæĹłæ³ķ
    -0.24
     assort
    -0.24
    yper
    -0.24
    POSITIVE LOGITS
    iser
    0.29
    viso
    0.28
     Tus
    0.26
     equation
    0.25
     problem
    0.25
    好å¥ĩ
    0.25
    emd
    0.24
     alert
    0.24
    解åĨ³éĹ®é¢ĺ
    0.24
    æĸ°éĽ¶åĶ®
    0.23
    Activations Density 0.013%

    No Known Activations