© 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. 30-TRANSCODER-HP
    7. 95675
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovan
    -0.30
    ernet
    -0.28
    porte
    -0.26
    å½ĵåīįä½įç½®
    -0.25
    PELL
    -0.25
    curring
    -0.25
    hatt
    -0.25
    mates
    -0.25
    reur
    -0.25
    CR
    -0.24
    POSITIVE LOGITS
    æ¸Į
    0.27
    éĥ¦
    0.26
    oga
    0.26
     infuri
    0.26
    _hot
    0.25
    æݧèĤ¡éĽĨåĽ¢
    0.24
    (rc
    0.24
    å°ĺ
    0.24
    æĹ¶è¾°
    0.24
    \Has
    0.24
    Activations Density 0.877%

    No Known Activations

    This feature has no known activations.