© 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. 161777
    Prev
    Next
    INDEX
    Explanations

    a, an

    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
    åı¸
    -0.30
    ãĥĽãĥ¼ãĥ«
    -0.28
    Indented
    -0.27
    cret
    -0.25
    liest
    -0.25
    ánt
    -0.25
    注éĶĢ
    -0.24
    REATE
    -0.24
     VERIFY
    -0.24
    å¤ļ人
    -0.23
    POSITIVE LOGITS
     proper
    0.30
     lack
    0.28
    åħħå®ŀ
    0.27
    ember
    0.27
    åıijå±ķæł¼å±Ģ
    0.27
    çļĦè¯Ŀ
    0.26
     Proper
    0.26
    emma
    0.26
    orks
    0.26
    缺ä¹ı
    0.25
    Activations Density 0.001%

    No Known Activations