© 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. 30-TRANSCODER-HP
    7. 96268
    Prev
    Next
    INDEX
    Explanations

    say "difficult"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ñīен
    -0.27
     talked
    -0.27
    WARDS
    -0.26
    vier
    -0.25
    äºĨ解ä¸Ģä¸ĭ
    -0.25
    неÑģен
    -0.25
    å°ıå¹ħ
    -0.25
     wraps
    -0.24
    å°ıå°ı
    -0.24
    åİĭå®ŀ
    -0.24
    POSITIVE LOGITS
     difficult
    0.39
    éļ¾
    0.39
     challenging
    0.39
    éļ¾åº¦
    0.36
     complicated
    0.35
     difficulty
    0.35
    åĽ°éļ¾
    0.35
     difficulties
    0.35
    éĽ£
    0.34
     dific
    0.33
    Activations Density 0.889%

    No Known Activations