© 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. 57943
    Prev
    Next
    INDEX
    Explanations

    school

    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
    ç½ijåıĭ
    -0.26
    enet
    -0.26
     conveying
    -0.25
    arching
    -0.25
    hin
    -0.24
    缤纷
    -0.24
    yssey
    -0.24
    AGER
    -0.23
    ARIABLE
    -0.23
    -Aug
    -0.23
    POSITIVE LOGITS
     pain
    0.28
     Watkins
    0.27
    _related
    0.27
     though
    0.27
     related
    0.26
    igaret
    0.26
     bio
    0.26
     interactions
    0.25
    related
    0.25
     interaction
    0.25
    Activations Density 0.003%

    No Known Activations