© 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. 57675
    Prev
    Next
    INDEX
    Explanations

    entity

    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
    -0.30
    æĢİä¹Ī说
    -0.25
    åĻ¨
    -0.24
    Äįe
    -0.24
    athan
    -0.23
    樣
    -0.23
    gable
    -0.23
    istan
    -0.23
    aux
    -0.22
    ENCY
    -0.22
    POSITIVE LOGITS
    drawing
    0.28
    íĪ¬
    0.28
     graded
    0.27
    YTE
    0.26
    rike
    0.25
    æ°§åĮĸ
    0.24
     brows
    0.23
    rowned
    0.23
    解æĶ¾æĢĿæĥ³
    0.23
    +len
    0.23
    Activations Density 0.077%

    No Known Activations