© 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. 58017
    Prev
    Next
    INDEX
    Explanations

    units of time

    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
    AMPLE
    -0.28
    diff
    -0.27
    after
    -0.26
    otive
    -0.25
    åįģä½Ļå¹´
    -0.25
     diffusion
    -0.25
     engagements
    -0.25
    åĪĨéĴŁåIJİ
    -0.25
     diffs
    -0.24
    otr
    -0.24
    POSITIVE LOGITS
    éĩĮ
    0.26
    primer
    0.26
    ading
    0.26
    å¾Ĺ太
    0.26
    便äºİ
    0.25
    å¾Ĺ好
    0.25
    arsi
    0.24
    eler
    0.24
    .FileReader
    0.24
    çªķ
    0.23
    Activations Density 0.017%

    No Known Activations