© 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. 107587
    Prev
    Next
    INDEX
    Explanations

    ocyte

    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
    anging
    -0.28
    èĢģåŃĹåı·
    -0.25
    aggable
    -0.24
    æµİ
    -0.24
    textAlign
    -0.24
    Formatting
    -0.24
    Sadly
    -0.23
    ,col
    -0.23
    ashed
    -0.23
    Ã¶ÃŁe
    -0.23
    POSITIVE LOGITS
    herits
    0.35
    éd
    0.29
     said
    0.26
    otr
    0.26
    Check
    0.26
     Enlight
    0.25
    è¦ģåľ¨
    0.25
    äºĨä¸Ģåı£
    0.24
    ounds
    0.24
    åĪĢ
    0.24
    Activations Density 12.934%

    No Known Activations