© 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. 9-TRANSCODER-HP
    7. 29555
    Prev
    Next
    INDEX
    Explanations

    these/those

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĨµ
    -0.28
    åĪ»
    -0.26
    iller
    -0.26
    hal
    -0.25
    ayload
    -0.24
    éħ·
    -0.24
     worse
    -0.24
     matière
    -0.24
     $__
    -0.24
    å¹»
    -0.23
    POSITIVE LOGITS
    OUS
    0.27
    	inst
    0.25
    een
    0.25
    acked
    0.25
    ç±³ç²ī
    0.25
    .ObjectMapper
    0.23
     acknowledges
    0.23
     acknowledging
    0.23
     INST
    0.23
     INSTANCE
    0.23
    Activations Density 0.091%

    No Known Activations