© 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. 57933
    Prev
    Next
    INDEX
    Explanations

    plant extracts and parts

    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
    ableView
    -0.29
    æĹ¥æĬ¥éģĵ
    -0.27
    çīĮçħ§
    -0.27
     palate
    -0.26
    以为
    -0.24
    Drv
    -0.24
    eyer
    -0.23
    磫æŃ£
    -0.23
    SHARE
    -0.23
    patches
    -0.23
    POSITIVE LOGITS
    udent
    0.27
    oop
    0.27
    éģº
    0.26
    ContentSize
    0.26
    æľ¬è´¨
    0.25
    thon
    0.25
    æĺ¯æľī
    0.25
    æłħ
    0.25
    _SHA
    0.25
    ça
    0.25
    Activations Density 0.010%

    No Known Activations