© 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. 57928
    Prev
    Next
    INDEX
    Explanations

    Paediatric/code

    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
     fus
    -0.26
     forced
    -0.25
    .constructor
    -0.25
     Fusion
    -0.24
    èĥį
    -0.24
    ously
    -0.24
     rais
    -0.23
    ниÑĨ
    -0.23
     stretch
    -0.23
    Think
    -0.23
    POSITIVE LOGITS
    elig
    0.27
    åħ¶ä»ĸ人
    0.27
    arch
    0.26
    istro
    0.26
    .criteria
    0.26
    æ¡Ī
    0.26
    ipel
    0.26
    roadcast
    0.25
    endir
    0.25
     interchangeable
    0.24
    Activations Density 0.150%

    No Known Activations