© 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. 23-TRANSCODER-HP
    7. 24049
    Prev
    Next
    INDEX
    Explanations

    introduction/reference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»»ä½ķå½¢å¼ı
    -0.26
    Ĥ¬
    -0.25
    egas
    -0.24
    éĽĩ
    -0.24
    eturn
    -0.24
    ä¹ĭåIJİ
    -0.24
    è°
    -0.24
    inds
    -0.23
    å¾ĹåĪ°
    -0.23
    å¾ĹåĪ°äºĨ
    -0.23
    POSITIVE LOGITS
     yourselves
    0.34
     relevant
    0.32
    è¿Ļä¸ªåľ°æĸ¹
    0.29
    缸åħ³ä¿¡æģ¯
    0.27
    è¿Ļ家
    0.27
    relevant
    0.27
    arness
    0.26
    your
    0.26
    缸åħ³æĶ¿çŃĸ
    0.26
     YOUR
    0.26
    Activations Density 0.020%

    No Known Activations