© 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. 33-TRANSCODER-HP
    7. 53554
    Prev
    Next
    INDEX
    Explanations

    genetics and orchestras

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Genome
    -0.33
     genome
    -0.33
     ch
    -0.31
    genome
    -0.30
     genomes
    -0.29
     instrumental
    -0.29
    åŁºåĽł
    -0.28
    -setting
    -0.28
    uator
    -0.27
     genetic
    -0.27
    POSITIVE LOGITS
    沪
    0.26
    åĽ¢
    0.25
    åĽ¾çĶ»
    0.25
    沿çĿĢ
    0.25
    è°IJ
    0.25
    ijke
    0.25
    mut
    0.24
     Regulatory
    0.24
    üss
    0.24
     Mut
    0.24
    Activations Density 0.331%

    No Known Activations