© 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. 22-TRANSCODER-HP
    7. 111805
    Prev
    Next
    INDEX
    Explanations

    handed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asti
    -0.28
    ried
    -0.26
    çľĭ好
    -0.25
    _places
    -0.25
    éĥ½åºĶ该
    -0.25
    kal
    -0.25
    让æĤ¨
    -0.25
    è´²
    -0.24
    è°ģéĥ½
    -0.24
    ansi
    -0.24
    POSITIVE LOGITS
    为åħ¶
    0.38
    åľ¨åħ¶
    0.28
    对åħ¶
    0.28
    对ä»ĸ
    0.26
    对ä»ĸ们
    0.26
    æĶĺ
    0.26
    ote
    0.26
     Stage
    0.26
     ihm
    0.25
    enk
    0.25
    Activations Density 0.014%

    No Known Activations