© 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. 40347
    Prev
    Next
    INDEX
    Explanations

    /

    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
    bart
    -0.28
    -Life
    -0.26
     SCR
    -0.26
     Filip
    -0.25
    "errors
    -0.24
     Invest
    -0.24
    à¹ģà¸Ĺ
    -0.24
    ä¹ĭ乡
    -0.24
     Micha
    -0.23
     Relatives
    -0.23
    POSITIVE LOGITS
    adel
    0.28
    æīįæľī
    0.28
    ä¸ĭåįĬå¹´
    0.25
    ä¸ĭåİ»
    0.25
    åħ¬åı¸å°Ĩ
    0.24
    æĥ
    0.24
    íį¼
    0.24
    ãĤ³ãĥ¬
    0.24
    urning
    0.24
    yyyy
    0.24
    Activations Density 1.305%

    No Known Activations