© 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. 5062
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     manually
    -0.26
    íĺķ
    -0.26
     yourselves
    -0.25
     yourself
    -0.24
    å®ŀéĻħæĥħåĨµ
    -0.24
    æ³½
    -0.24
     Millionen
    -0.24
    æľ¬
    -0.24
    Scanner
    -0.23
    å±ŀäºİ
    -0.23
    POSITIVE LOGITS
    å°½
    0.25
    æľīä¿¡å¿ĥ
    0.25
     freezes
    0.25
     ALWAYS
    0.24
     ÙĦÙĦØ£
    0.23
     Waist
    0.23
    ält
    0.23
    firm
    0.23
    æĦıè¯Ĩ
    0.23
    izedName
    0.23
    Activations Density 0.005%

    No Known Activations