© 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. 97711
    Prev
    Next
    INDEX
    Explanations

    6

    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
     etc
    -0.27
    etc
    -0.26
    ropolis
    -0.25
    çŃī
    -0.25
    -,
    -0.25
    __,__
    -0.24
    OCUS
    -0.24
    imity
    -0.24
    seat
    -0.24
    opsis
    -0.24
    POSITIVE LOGITS
    ï¼Į并
    0.51
    å¹¶åľ¨
    0.48
    并éĢļè¿ĩ
    0.48
    并äºİ
    0.46
     &&↵
    0.41
    )&&
    0.41
    并ä¸Ķ
    0.40
    并å°Ĩ
    0.40
    并对
    0.40
    èĥ½åĬĽåĴĮ
    0.38
    Activations Density 0.001%

    No Known Activations