© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5052
    Prev
    Next
    INDEX
    Explanations

    Punctuation, "or"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nick
    -0.28
     vag
    -0.28
    天ä¸ĭ
    -0.27
    室åıĭ
    -0.26
    车
    -0.26
    uch
    -0.25
    å½ĺ
    -0.25
     calor
    -0.24
     competent
    -0.24
    é¤IJåħ·
    -0.24
    POSITIVE LOGITS
    isons
    0.26
    _rsa
    0.25
    phet
    0.25
    ekte
    0.25
    etry
    0.25
     bol
    0.25
    adle
    0.24
    ñana
    0.23
    ,False
    0.23
    éŀį
    0.23
    Activations Density 0.022%

    No Known Activations