© 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. 149714
    Prev
    Next
    INDEX
    Explanations

    lost or hidden

    np_max-act-logits · gemini-2.0-flash
    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
     dream
    -0.34
    åģļ梦
    -0.29
    dream
    -0.29
     dreamed
    -0.29
    梦æĥ³
    -0.29
     dreaming
    -0.28
     rêve
    -0.27
    夢
    -0.27
    otto
    -0.24
    cloth
    -0.24
    POSITIVE LOGITS
    nier
    0.35
    åı¦ä¸ĢåįĬ
    0.29
    åĬ²
    0.29
     tapes
    0.25
    inus
    0.25
    .fm
    0.24
    oten
    0.24
    ä¸Ģæ³¢
    0.24
    ta
    0.24
     Rey
    0.24
    Activations Density 1.092%

    No Known Activations