© 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. 57744
    Prev
    Next
    INDEX
    Explanations

    Software, crypto, or food

    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
    vron
    -0.29
    ãģ©
    -0.24
    .getElement
    -0.24
    ItemAt
    -0.23
    дÑĥÑĤ
    -0.23
    (Parse
    -0.23
    default
    -0.23
    rott
    -0.23
    è¦Ĩ
    -0.23
    .styleable
    -0.23
    POSITIVE LOGITS
    aro
    0.32
    gü
    0.25
    ari
    0.25
    keit
    0.25
     lattice
    0.25
    arus
    0.25
    ón
    0.24
    è´¨éĩıéĹ®é¢ĺ
    0.24
     Fitzgerald
    0.24
    upo
    0.24
    Activations Density 0.029%

    No Known Activations