© 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. 56973
    Prev
    Next
    INDEX
    Explanations

    up

    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
     stacks
    -0.32
    otland
    -0.29
    å½¢æĪIJ
    -0.27
    社ä¼ļåıijå±ķ
    -0.26
    æķ´çIJĨ
    -0.26
    öst
    -0.25
    ä¹ĭåĬĽ
    -0.25
    模å¼ı
    -0.25
    éĢģåĪ°
    -0.25
    uja
    -0.25
    POSITIVE LOGITS
    PAL
    0.25
     Abr
    0.25
    ä¸ĢåŃĹ
    0.24
    (Optional
    0.24
     freel
    0.24
    .Merge
    0.23
     lap
    0.23
     abras
    0.23
    IZED
    0.23
    æ¹¾åĮº
    0.23
    Activations Density 0.012%

    No Known Activations