© 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. 30-TRANSCODER-HP
    7. 95069
    Prev
    Next
    INDEX
    Explanations

    contrasting sentences

    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
    Negative Logits
    áŀļ
    -0.26
     Quarter
    -0.25
    è¾ħ
    -0.25
    å²ĺ
    -0.25
     Vertical
    -0.25
    ilateral
    -0.24
     retains
    -0.24
    outine
    -0.24
     noting
    -0.24
    _UNIQUE
    -0.24
    POSITIVE LOGITS
    å®ŀéĻħä¸Ĭ
    0.47
    å®ŀéĻħä¸Ĭæĺ¯
    0.42
    äºĭå®ŀä¸Ĭ
    0.42
    å®ŀéĻħæĥħåĨµ
    0.42
     actually
    0.40
     actual
    0.37
    actual
    0.37
    ä½Ĩå®ŀéĻħä¸Ĭ
    0.36
    Actually
    0.36
    å®ŀéĻħ
    0.36
    Activations Density 0.896%

    No Known Activations