© 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. 161845
    Prev
    Next
    INDEX
    Explanations

    Modal verbs

    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
    èĻ½çĦ¶æĺ¯
    -0.28
     recruit
    -0.28
    ä¸įåĪĨ
    -0.27
    æħİéĩį
    -0.27
    yntax
    -0.27
    lessness
    -0.27
    VS
    -0.26
    æ´¾éģ£
    -0.25
    ä¸Ģ次
    -0.25
    IDL
    -0.25
    POSITIVE LOGITS
     culp
    0.26
    ITCH
    0.26
    Outlined
    0.25
    è¿Ļ两ç§į
    0.25
     initiatives
    0.25
     모ëijIJ
    0.25
     caus
    0.24
    chemes
    0.23
     пом
    0.23
     relie
    0.23
    Activations Density 0.005%

    No Known Activations