© 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
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162726
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    è¿ĻçĤ¹
    -0.34
    chants
    -0.28
    è¿Ļä¸ĢçĤ¹
    -0.27
    COMP
    -0.27
    豸
    -0.25
    ewriter
    -0.25
     EVP
    -0.25
    iVar
    -0.24
    ULE
    -0.24
    ä¸ĢæŦ
    -0.23
    POSITIVE LOGITS
    å®ĥ
    0.38
     it
    0.34
     It
    0.32
    cloak
    0.30
    æ¯ĶåĪ©
    0.29
    å¹½
    0.28
    æĽ´å¥½
    0.27
    It
    0.26
    å®ĥæĺ¯
    0.26
    —it
    0.25
    Activations Density 0.005%

    No Known Activations