© 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. 140984
    Prev
    Next
    INDEX
    Explanations

    Beginning of paragraphs

    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
     savedInstanceState
    -0.29
     [|
    -0.27
    æijĨ
    -0.27
    ::$
    -0.26
    chef
    -0.26
    [value
    -0.25
    ECT
    -0.24
    ħ§
    -0.24
    ETY
    -0.24
     legislators
    -0.24
    POSITIVE LOGITS
    Winner
    0.26
    åıĤä¸İèĢħ
    0.26
    -under
    0.26
    unders
    0.25
    iscal
    0.25
    winner
    0.25
     kop
    0.24
    çĶŁæ´»ä¸Ń
    0.24
     bask
    0.23
    íĻ©
    0.23
    Activations Density 11.429%

    No Known Activations