© 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. 161786
    Prev
    Next
    INDEX
    Explanations

    displacement, replacement, history

    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
    UDGE
    -0.26
     circum
    -0.26
    ÑģÑĤеÑĢ
    -0.25
     watching
    -0.25
    ERGY
    -0.25
    (quantity
    -0.25
    -budget
    -0.24
    -online
    -0.24
    æĶ¯çº¿
    -0.24
    Escort
    -0.24
    POSITIVE LOGITS
    çĶ¨éĢĶ
    0.46
    åľ°åĿĹ
    0.37
    åľŁåľ°
    0.35
    çĶ¨åľ°
    0.33
     occupied
    0.32
    filled
    0.31
     land
    0.31
    建设çĶ¨åľ°
    0.31
     lands
    0.31
    空çĻ½
    0.30
    Activations Density 0.012%

    No Known Activations