© 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. 57224
    Prev
    Next
    INDEX
    Explanations

    what

    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
    çİ·
    -0.27
    amat
    -0.25
    defense
    -0.24
    oused
    -0.23
    ÃŃf
    -0.23
    åĽ½æĥħ
    -0.23
    BindView
    -0.23
     Dut
    -0.23
    ç®Ģ称
    -0.23
    åĦĺ
    -0.23
    POSITIVE LOGITS
     res
    0.29
    è¿ĩ
    0.28
     we
    0.26
     natural
    0.26
    ä»Ģä¹Ī
    0.26
     normal
    0.26
     lab
    0.26
     it
    0.25
    åĢ¾
    0.25
     ```
    0.25
    Activations Density 0.013%

    No Known Activations