© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 7722
    Prev
    Next
    INDEX
    Explanations

    'll

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ReactDOM
    -0.27
    erca
    -0.27
    èľķ
    -0.26
    åıijè§ī
    -0.26
     noticing
    -0.25
    !!.
    -0.24
    å¿ĥ缮ä¸Ń
    -0.24
    sap
    -0.24
    äºĨåIJ§
    -0.24
    æĪijè§īå¾Ĺ
    -0.24
    POSITIVE LOGITS
    æķŀå¼Ģ
    0.29
     below
    0.28
    ä¸įèµ·
    0.27
     often
    0.26
    为æĪij们
    0.25
     open
    0.25
     truth
    0.24
    allows
    0.24
    çİĩ为
    0.23
    Ñħодим
    0.23
    Activations Density 0.010%

    No Known Activations