© 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. 14-TRANSCODER-HP
    7. 39786
    Prev
    Next
    INDEX
    Explanations

    another

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    @endsection
    -0.26
     markup
    -0.25
    ç¼ł
    -0.24
    remen
    -0.24
    @stop
    -0.24
    åĩłåĪĨ
    -0.24
    .'.$
    -0.23
    ')}}"></
    -0.23
     LICENSE
    -0.23
    >.</
    -0.23
    POSITIVE LOGITS
    ILITY
    0.31
    Ừ
    0.28
    hips
    0.28
    og
    0.28
    ugal
    0.28
    èĪIJ
    0.27
    rier
    0.27
    ear
    0.26
    arium
    0.25
    iance
    0.25
    Activations Density 1.307%

    No Known Activations