© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 161905
    Prev
    Next
    INDEX
    Explanations

    Mentions of specific things

    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
    ecz
    -0.31
    以ä¸ĬçļĦ
    -0.28
    沿éĢĶ
    -0.27
    hani
    -0.26
    arih
    -0.26
    ImageContext
    -0.25
    npos
    -0.25
    FilterWhere
    -0.25
    orrar
    -0.24
    antar
    -0.24
    POSITIVE LOGITS
     invariant
    0.30
     This
    0.27
     Rin
    0.27
    æĺ¯ä¸Ģç§į
    0.27
    This
    0.27
    æĺ¯ä¸Ģ项
    0.26
    lob
    0.26
    èĿī
    0.26
    Invariant
    0.26
    lib
    0.25
    Activations Density 0.007%

    No Known Activations