© 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. 64041
    Prev
    Next
    INDEX
    Explanations

    Language and writing examples

    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
    iben
    -0.27
    erals
    -0.25
     Rat
    -0.25
    ILD
    -0.24
    azen
    -0.24
    wins
    -0.24
    ascar
    -0.24
    URED
    -0.23
    ATED
    -0.23
    åħ¬åı¸å°Ĩ
    -0.23
    POSITIVE LOGITS
     **
    0.30
    å¥ij约
    0.27
    **
    0.27
    åīį沿
    0.27
     convention
    0.27
    å§ĵ
    0.26
    åģļ人
    0.26
    _PRI
    0.26
    _DET
    0.25
    icorn
    0.24
    Activations Density 4.026%

    No Known Activations