© 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. 163066
    Prev
    Next
    INDEX
    Explanations

    personal blog entries

    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
    kers
    -0.31
    eways
    -0.30
    otron
    -0.28
     egret
    -0.27
    常è§ģçļĦ
    -0.26
     kayıt
    -0.26
     anmeld
    -0.26
     communicator
    -0.25
    etic
    -0.25
    åīįéĢĶ
    -0.24
    POSITIVE LOGITS
    lix
    0.29
    泡
    0.29
    人åĿĩ
    0.27
    ijľ
    0.26
    çĪ±å¥½
    0.25
    semi
    0.25
    å°Ķ
    0.25
    _stdio
    0.25
    éĴĵé±¼
    0.25
    家åĬ¡
    0.24
    Activations Density 0.009%

    No Known Activations