© 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. 24-TRANSCODER-HP
    7. 150874
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agher
    -0.29
    umbo
    -0.28
    èįŁ
    -0.24
    责任åĪ¶
    -0.24
    è¢Ĥ
    -0.23
    exampleModal
    -0.23
    éĥijéĩį
    -0.23
     purposely
    -0.23
    èİ·èĥľ
    -0.23
    濯
    -0.23
    POSITIVE LOGITS
    '$
    0.26
    attachment
    0.26
    agen
    0.26
    _$
    0.25
    æĬĺåıł
    0.24
    ("$
    0.24
     `$
    0.24
     adher
    0.24
    åĩ¡
    0.24
    byter
    0.23
    Activations Density 1.114%

    No Known Activations

    This feature has no known activations.