© 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. 35-TRANSCODER-HP
    7. 39210
    Prev
    Next
    INDEX
    Explanations

    cor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĥĺ
    -0.29
     pie
    -0.26
    oupper
    -0.26
    åİŁæĿ¥æĺ¯
    -0.25
    ç¿»è¯ij
    -0.25
     Exception
    -0.24
    æĶ¹æĪIJ
    -0.24
    åºĶ该æĺ¯
    -0.24
    -created
    -0.24
    åŀĨ
    -0.24
    POSITIVE LOGITS
    ps
    0.43
    PS
    0.40
     PS
    0.35
     Ps
    0.35
    (ps
    0.33
     ps
    0.33
    	ps
    0.31
     PSD
    0.30
    Ps
    0.30
    _ps
    0.30
    Activations Density 33.767%

    No Known Activations