© 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. 20-TRANSCODER-HP
    7. 141451
    Prev
    Next
    INDEX
    Explanations

    negativity/problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _rq
    -0.29
    çĶ³
    -0.28
     itemprop
    -0.25
    ome
    -0.25
    OME
    -0.24
    亮
    -0.24
    宾
    -0.24
    ued
    -0.24
    èĩĤ
    -0.24
    uest
    -0.23
    POSITIVE LOGITS
    çļĦ对象
    0.32
    İĺìĿ´
    0.30
    å®īåħ¨æĢ§
    0.28
    èĩªåıij
    0.26
    çļĦçľ¼çĿĽ
    0.26
     setC
    0.25
    curity
    0.25
     chứ
    0.24
    çļĦå®īåħ¨
    0.24
    ä¸ĩ欧åħĥ
    0.24
    Activations Density 21.423%

    No Known Activations