© 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. 8824
    Prev
    Next
    INDEX
    Explanations

    Japanese articles and names

    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
     trial
    -0.29
    MENTS
    -0.27
    æĥ³èµ·æĿ¥
    -0.25
     Nghá»ĩ
    -0.24
    unya
    -0.24
    Trial
    -0.24
    åĪ¤
    -0.24
    级
    -0.23
    EMS
    -0.23
    å°¤
    -0.23
    POSITIVE LOGITS
    aff
    0.29
    çªĹåı£
    0.28
    'aff
    0.28
    eward
    0.27
    .spec
    0.27
    -opacity
    0.26
    -aff
    0.26
    astically
    0.26
     Contributor
    0.25
     AFF
    0.25
    Activations Density 0.018%

    No Known Activations