© 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. 58117
    Prev
    Next
    INDEX
    Explanations

    To

    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
    ucket
    -0.25
    енно
    -0.24
    еÑĩно
    -0.24
    ä¸ŃåĽ½åĽ½éĻħ
    -0.24
    неÑĢ
    -0.24
    oved
    -0.23
    éŨåīį
    -0.23
    ?key
    -0.23
     doorstep
    -0.23
    UNS
    -0.23
    POSITIVE LOGITS
    çIJĨ解
    0.41
    çIJĨ解åĴĮ
    0.39
     understanding
    0.38
     understand
    0.37
     how
    0.33
     what
    0.32
    quoi
    0.31
    äºĨ解
    0.31
    æĺ¯æĢİæł·
    0.31
    åĽŀçŃĶ
    0.30
    Activations Density 0.027%

    No Known Activations