© 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. 130223
    Prev
    Next
    INDEX
    Explanations

    validity and specificity

    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
    _enc
    -0.27
    ÙĪÙĤ
    -0.26
     necessary
    -0.26
    ever
    -0.25
     tunnel
    -0.25
    屿
    -0.25
    (enc
    -0.25
     Enc
    -0.25
    oud
    -0.24
    (push
    -0.24
    POSITIVE LOGITS
    atsby
    0.27
    Sans
    0.25
    orca
    0.25
    å½¼æѤ
    0.24
    Disclosure
    0.24
    DEM
    0.24
    aded
    0.24
    Reuse
    0.24
     moder
    0.24
    åı¦
    0.24
    Activations Density 15.677%

    No Known Activations