© 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. 27-TRANSCODER-HP
    7. 9144
    Prev
    Next
    INDEX
    Explanations

    Computer-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģä¸ĭ
    -0.29
    æ¾İæ¹ĥæĸ°éĹ»
    -0.28
     FY
    -0.25
    ForResource
    -0.25
    bens
    -0.25
    _beh
    -0.24
    çļĦæ¯Ķä¾ĭ
    -0.24
    ä¸Ģ年级
    -0.24
    Ly
    -0.23
    |#
    -0.23
    POSITIVE LOGITS
    ness
    0.29
    è¶ģ
    0.28
     cam
    0.26
    Moment
    0.25
    eve
    0.25
    çŀª
    0.24
    (cont
    0.23
    /flutter
    0.23
    overn
    0.23
    vel
    0.23
    Activations Density 0.134%

    No Known Activations