© 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. 14-TRANSCODER-HP
    7. 40088
    Prev
    Next
    INDEX
    Explanations

    Code and names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹĹ
    -0.30
    æ²īé»ĺ
    -0.27
     (>
    -0.27
    ä¸Ģå¾ĭ
    -0.27
    usalem
    -0.26
    两次
    -0.26
    alse
    -0.25
    isl
    -0.24
     ÑģÑĤоим
    -0.24
     consist
    -0.24
    POSITIVE LOGITS
     Previously
    0.27
    onder
    0.27
     previously
    0.26
    èĪĪ
    0.26
    marsh
    0.26
    åħ´
    0.26
    YPE
    0.25
    til
    0.25
     kole
    0.25
     -*-↵↵
    0.24
    Activations Density 1.210%

    No Known Activations