© 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. 43307
    Prev
    Next
    INDEX
    Explanations

    The letter R

    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
     ActivatedRoute
    -0.27
    ilden
    -0.26
    malink
    -0.24
    cord
    -0.24
     Pact
    -0.24
     Nic
    -0.24
     Nich
    -0.23
    æľºåĬ¨
    -0.23
    ardon
    -0.23
    oen
    -0.23
    POSITIVE LOGITS
     R
    0.87
    èĥ¡
    0.72
    R
    0.72
    .R
    0.57
    ,R
    0.56
    *R
    0.54
    	R
    0.52
    _R
    0.52
    >R
    0.52
    |R
    0.51
    Activations Density 0.005%

    No Known Activations