© 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. 30-TRANSCODER-HP
    7. 95588
    Prev
    Next
    INDEX
    Explanations

    decorations and art

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecast
    -0.29
    Cast
    -0.29
    ToPoint
    -0.27
    cast
    -0.26
     Cast
    -0.25
    arshal
    -0.25
    ableObject
    -0.25
    atile
    -0.25
    caster
    -0.25
    ocity
    -0.24
    POSITIVE LOGITS
     imp
    0.30
     informat
    0.30
     around
    0.27
    家éķ¿ä»¬
    0.27
    ç¾İçļĦ
    0.27
    âĢ¾
    0.26
     decorations
    0.26
     somewhere
    0.26
     rim
    0.25
    æ©«
    0.25
    Activations Density 0.889%

    No Known Activations