© 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. 53195
    Prev
    Next
    INDEX
    Explanations

    Cont

    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
    cont
    -0.50
    Cont
    -0.50
     cont
    -0.50
     Cont
    -0.48
    -cont
    -0.47
    _cont
    -0.44
    (cont
    -0.40
    	cont
    -0.39
     CONT
    -0.37
     kont
    -0.36
    POSITIVE LOGITS
    avax
    0.28
    orio
    0.27
    ÑĪим
    0.26
    rü
    0.25
     Nes
    0.25
     QS
    0.25
     Qual
    0.25
    RICS
    0.25
     receivers
    0.24
    rx
    0.24
    Activations Density 0.006%

    No Known Activations