© 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. 53802
    Prev
    Next
    INDEX
    Explanations

    parl

    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
    ivity
    -0.33
    iki
    -0.28
    nan
    -0.27
    ê°IJ
    -0.26
    ningen
    -0.26
    nes
    -0.26
    nings
    -0.26
    IVITY
    -0.26
    icing
    -0.25
    nof
    -0.25
    POSITIVE LOGITS
    èĢ³
    0.28
    air
    0.28
    lez
    0.27
     Le
    0.27
    åı°
    0.26
    Le
    0.26
    ose
    0.26
    空æ°Ķ
    0.25
    dera
    0.25
     ext
    0.25
    Activations Density 0.009%

    No Known Activations