© 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. 8191
    Prev
    Next
    INDEX
    Explanations

    planets and space

    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
    å¢ŀ
    -0.26
    _die
    -0.26
     sym
    -0.25
    ivity
    -0.24
    made
    -0.24
    Reply
    -0.24
    stu
    -0.24
    åĶ¬
    -0.23
     part
    -0.23
    æŶéĹ´ä¸º
    -0.23
    POSITIVE LOGITS
    ologist
    0.29
     maint
    0.26
    berman
    0.26
     ì·¨
    0.25
    ä¸Ģåı°
    0.25
    cestor
    0.25
    imilar
    0.25
    å¿ĥä¸Ń
    0.25
    icular
    0.24
    èµĭ
    0.24
    Activations Density 0.001%

    No Known Activations