© 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. 163058
    Prev
    Next
    INDEX
    Explanations

    Usage, instructions, processes

    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
    mine
    -0.28
    å¾Ĥ
    -0.28
    /auto
    -0.27
    ara
    -0.27
    ä»Ģä¹Īäºĭ
    -0.26
    éģĹ
    -0.25
    å¾ĪæŃ£å¸¸
    -0.25
     ra
    -0.25
     Challenger
    -0.25
    enh
    -0.24
    POSITIVE LOGITS
    è°¨æħİ
    0.40
    æħİéĩį
    0.36
     carefully
    0.36
     careful
    0.34
     cautiously
    0.34
     cautious
    0.29
    æ¸ħçĪ½
    0.27
    iento
    0.27
    éĩįè§Ĩ
    0.27
     caution
    0.26
    Activations Density 0.002%

    No Known Activations