© 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. 32-TRANSCODER-HP
    7. 41665
    Prev
    Next
    INDEX
    Explanations

    programming and technology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¾Ī
    -0.30
    onas
    -0.27
    æ°¸ä¸į
    -0.27
    éĥ½æľī
    -0.25
     very
    -0.25
     muy
    -0.24
     Experienced
    -0.24
    毫æĹł
    -0.24
    亲åĪĩ
    -0.24
     rất
    -0.24
    POSITIVE LOGITS
     do
    0.41
     people
    0.41
     works
    0.38
     Do
    0.37
    do
    0.37
     is
    0.36
     tends
    0.34
     corresponds
    0.34
     would
    0.32
    	do
    0.32
    Activations Density 0.011%

    No Known Activations