© 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. 62953
    Prev
    Next
    INDEX
    Explanations

    Instructions and browser settings

    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
     entirely
    -0.27
    nbsp
    -0.27
    ?option
    -0.26
    css
    -0.26
     tertiary
    -0.25
    pping
    -0.25
    edo
    -0.25
    etic
    -0.24
    segue
    -0.24
    typeid
    -0.24
    POSITIVE LOGITS
    åij¤
    0.26
    elter
    0.25
    __',
    0.25
    Ä°N
    0.24
    æĿ¥çĶµ
    0.24
     Emb
    0.24
     веÑĩеÑĢ
    0.24
    çī¹æ®ĬæĥħåĨµ
    0.23
    lor
    0.23
     Ft
    0.23
    Activations Density 3.914%

    No Known Activations