© 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. 54439
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    cur
    -0.27
    	cur
    -0.27
    ipt
    -0.27
     cur
    -0.26
    Cur
    -0.23
    orida
    -0.23
    (cur
    -0.23
    IRD
    -0.23
    kur
    -0.23
    ++.
    -0.23
    POSITIVE LOGITS
    æ§ĥ
    0.27
    º«
    0.26
    æĮĩçĤ¹
    0.26
    æĪį
    0.25
    sector
    0.25
    lash
    0.25
    ashing
    0.25
    .elem
    0.25
    å¶Ĥ
    0.25
    ä¹İ
    0.24
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.