© 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. 151042
    Prev
    Next
    INDEX
    Explanations

    the

    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
     these
    -0.41
    è¿ĻäºĽ
    -0.40
    è¿Ļæī¹
    -0.40
    éĤ£ä½į
    -0.38
     THESE
    -0.38
    These
    -0.38
    对该
    -0.37
    çļĦéĤ£ä¸ª
    -0.37
     These
    -0.37
    è¿Ļ段
    -0.37
    POSITIVE LOGITS
    rist
    0.27
    å¼Ĥ
    0.27
    -done
    0.26
    ilians
    0.25
     multiline
    0.25
    ctime
    0.25
    uzzi
    0.25
    burgh
    0.24
    买车
    0.24
    ilian
    0.23
    Activations Density 1.025%

    No Known Activations