© 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. 33-TRANSCODER-HP
    7. 54472
    Prev
    Next
    INDEX
    Explanations

    lightning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tip
    -0.34
    abel
    -0.31
    ione
    -0.30
    çģ¯
    -0.29
    елÑĮ
    -0.28
    ices
    -0.27
    ,label
    -0.26
    ME
    -0.26
    å¤Ħ
    -0.26
     label
    -0.26
    POSITIVE LOGITS
    éĽĨæĪIJ
    0.24
    rzy
    0.24
    _exe
    0.24
     suicides
    0.24
     slashed
    0.24
    ä¸įå¿ĺ
    0.24
    allah
    0.24
     drills
    0.24
    zego
    0.24
    åĩºåİĤ
    0.23
    Activations Density 0.004%

    No Known Activations