© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107696
    Prev
    Next
    INDEX
    Explanations

    adverbs of frequency

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    们éĥ½
    -0.27
    LI
    -0.26
    alone
    -0.25
    该项
    -0.25
    lemn
    -0.24
    éĴı
    -0.24
    uci
    -0.23
     owes
    -0.23
     bá»ı
    -0.23
    éľĦ
    -0.23
    POSITIVE LOGITS
     when
    0.53
    å½ĵä½ł
    0.49
    when
    0.48
    å½ĵæĪij们
    0.46
     When
    0.46
    å½ĵæĪij
    0.45
    When
    0.45
    _when
    0.42
    	when
    0.40
     когда
    0.40
    Activations Density 1.158%

    No Known Activations