© 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. 98823
    Prev
    Next
    INDEX
    Explanations

    Expressing caveats or clarifications

    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
    alm
    -0.28
    å±¥è¡Į
    -0.27
    alf
    -0.26
    ãĥ§
    -0.26
    天天
    -0.24
    tra
    -0.24
     concurrent
    -0.24
    é²į
    -0.24
     cr
    -0.23
     nature
    -0.23
    POSITIVE LOGITS
    emade
    0.31
    ä¹Łä¸įä¾ĭå¤ĸ
    0.28
    gars
    0.27
    çľ¼åīįçļĦ
    0.27
    amenti
    0.26
    -front
    0.26
    @login
    0.26
    åı£
    0.26
     yourselves
    0.25
    (Core
    0.25
    Activations Density 0.005%

    No Known Activations