© 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. 19-TRANSCODER-HP
    7. 7892
    Prev
    Next
    INDEX
    Explanations

    Forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĤÑĮ
    -0.26
     Klo
    -0.26
    mony
    -0.25
    tero
    -0.25
    andelier
    -0.25
    tery
    -0.25
    aney
    -0.25
    paramref
    -0.25
    æľįåĬ¡ä½ĵç³»
    -0.24
    prit
    -0.24
    POSITIVE LOGITS
    nw
    0.29
    åĪĨæķ°
    0.26
     ROT
    0.26
    ä¹ĭ称
    0.26
    word
    0.26
    Rot
    0.25
    Dub
    0.25
    otton
    0.25
    (use
    0.25
    IMENT
    0.25
    Activations Density 0.026%

    No Known Activations