© 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. 12-TRANSCODER-HP
    7. 22944
    Prev
    Next
    INDEX
    Explanations

    and or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ajo
    -0.26
    [X
    -0.25
    <X
    -0.25
    éĦł
    -0.25
    ussions
    -0.25
    æĦīå¿«
    -0.25
    IDA
    -0.24
     prescribe
    -0.24
    iena
    -0.24
     assh
    -0.24
    POSITIVE LOGITS
    lis
    0.29
    sgi
    0.28
    oo
    0.28
    wer
    0.27
    gon
    0.26
    odyn
    0.26
     entry
    0.26
    laps
    0.26
    lies
    0.25
     CType
    0.24
    Activations Density 0.003%

    No Known Activations