© 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. 150896
    Prev
    Next
    INDEX
    Explanations

    there is

    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
    æĪij认为
    -0.33
    çłĶ究表æĺİ
    -0.32
    æĪij们认为
    -0.30
    èªįçĤº
    -0.29
    itar
    -0.28
     Ced
    -0.28
     deemed
    -0.28
    éĥ½è®¤ä¸º
    -0.27
     deem
    -0.26
    кÑĥп
    -0.26
    POSITIVE LOGITS
    eren
    0.30
    诣
    0.29
    enh
    0.28
    ÑĢен
    0.28
     inherent
    0.28
    åŃļ
    0.27
     intrinsic
    0.26
    liches
    0.26
     viability
    0.26
    erre
    0.25
    Activations Density 1.115%

    No Known Activations