© 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. 53812
    Prev
    Next
    INDEX
    Explanations

    scientific/ technical reports

    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
    воÑĢ
    -0.31
    çģ°
    -0.27
    вод
    -0.26
    ogi
    -0.25
    æ§
    -0.25
     bib
    -0.25
     Castro
    -0.24
     pear
    -0.24
     VOL
    -0.24
    ide
    -0.24
    POSITIVE LOGITS
     sublist
    0.30
    .AddItem
    0.29
    交ä¼ļ
    0.28
    plementation
    0.27
    .power
    0.26
    ppv
    0.25
    .CreateInstance
    0.25
    /effects
    0.25
    abilia
    0.25
    nnen
    0.24
    Activations Density 0.009%

    No Known Activations