© 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. 129978
    Prev
    Next
    INDEX
    Explanations

    various text snippets

    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
    å®ŀåľ¨
    -0.30
    æĶ¯
    -0.27
    åĢŁ
    -0.27
    åĪ¤æĸŃ
    -0.26
    ager
    -0.26
    妥
    -0.25
    éĬ®
    -0.25
    åĪĥ
    -0.25
    .stub
    -0.25
    èĥİ
    -0.24
    POSITIVE LOGITS
     cycl
    0.27
     acrylic
    0.25
     Obs
    0.24
     Cycl
    0.24
    ijkl
    0.24
    íĮ¬
    0.24
    bial
    0.23
    åıijå¸ĥåħ¬åijĬ
    0.23
    она
    0.23
    Obs
    0.23
    Activations Density 2.147%

    No Known Activations