© 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. 18-TRANSCODER-HP
    7. 88534
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    indsight
    -0.27
     contextual
    -0.27
    /pp
    -0.26
     remarks
    -0.26
    .nt
    -0.26
    arking
    -0.25
     simplified
    -0.24
    etti
    -0.24
     simpl
    -0.24
     subsidi
    -0.24
    POSITIVE LOGITS
    å¿ĥ缮
    0.25
    held
    0.25
    spring
    0.25
    (Api
    0.24
    ham
    0.24
    hem
    0.24
    å¶Ĥ
    0.24
    çļĦæľĢ大
    0.23
    å®ŀçī©
    0.23
     Ñĩем
    0.23
    Activations Density 3.149%

    No Known Activations