© 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. 25-TRANSCODER-HP
    7. 107561
    Prev
    Next
    INDEX
    Explanations

    Queen/Queens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thought
    -0.29
    ron
    -0.28
    ibles
    -0.28
     school
    -0.28
    sf
    -0.27
    err
    -0.25
    ÑĨÑĭ
    -0.25
    con
    -0.25
    ct
    -0.25
    ÅĴ
    -0.25
    POSITIVE LOGITS
    agna
    0.26
     recalls
    0.25
    orient
    0.25
    ymology
    0.25
    INDER
    0.25
     manoe
    0.24
     orient
    0.24
     INCIDENT
    0.24
     KERNEL
    0.24
     surv
    0.24
    Activations Density 0.061%

    No Known Activations