© 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. 54428
    Prev
    Next
    INDEX
    Explanations

    ch

    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
     nan
    -0.28
    umann
    -0.28
     meter
    -0.27
    icles
    -0.26
    ç®Ń
    -0.26
    é¼IJ
    -0.25
    ãĤ¹ãĥĪ
    -0.25
     abstract
    -0.25
    chten
    -0.25
    çIJ¶
    -0.24
    POSITIVE LOGITS
    åŁºåľ°
    0.28
     TEX
    0.28
    oser
    0.27
    party
    0.26
    ä¸Ģéĥ¨
    0.26
    base
    0.26
    osing
    0.24
    aca
    0.24
    ä¸Ģ级
    0.24
    è·¨åĽ½
    0.24
    Activations Density 0.020%

    No Known Activations