© 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. 53451
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ues
    -0.32
     uten
    -0.25
    azz
    -0.25
    ugg
    -0.25
     cruiser
    -0.25
    建æĪIJåIJİ
    -0.25
     wirk
    -0.25
    ç£ĭ
    -0.24
    rea
    -0.24
    uzz
    -0.24
    POSITIVE LOGITS
    vana
    0.33
    thumb
    0.26
     Tall
    0.26
    å¹´ç»Ī
    0.26
    åŃ¦æľŁ
    0.26
    ulus
    0.26
     Needle
    0.26
     spur
    0.25
    berries
    0.25
    综
    0.25
    Activations Density 0.012%

    No Known Activations