© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 52888
    Prev
    Next
    INDEX
    Explanations

    W/w

    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
    积累äºĨ
    -0.32
    åŀĤ
    -0.28
    iat
    -0.27
    .POS
    -0.26
    çİĩè¾¾åĪ°
    -0.26
     motivating
    -0.25
    POS
    -0.25
     javafx
    -0.25
    cee
    -0.24
    æĥł
    -0.24
    POSITIVE LOGITS
    管å±Ģ
    0.27
    åĨĻåĩº
    0.25
    /write
    0.25
    _Write
    0.24
    kerja
    0.24
    opal
    0.24
    bble
    0.24
    éĻIJæľŁ
    0.24
    ewire
    0.24
     dbo
    0.24
    Activations Density 0.025%

    No Known Activations