© 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. 56844
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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±ij
    -0.33
     mark
    -0.27
     tree
    -0.26
    åĬ¡
    -0.26
    ToString
    -0.26
    Paste
    -0.25
    å¸ĤåľºçļĦ
    -0.24
    çľŁç©º
    -0.24
     spreading
    -0.24
    ç½ijç»ľä¼łæĴŃ
    -0.24
    POSITIVE LOGITS
    ropped
    0.28
    лиÑĤ
    0.26
    ä¸ĭåİ»
    0.26
    åįĬ天
    0.26
    lap
    0.26
     splitted
    0.25
    ãĤĭãĤĤãģ®
    0.25
     OMX
    0.25
     gems
    0.25
    ifter
    0.24
    Activations Density 0.078%

    No Known Activations