© 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. 23215
    Prev
    Next
    INDEX
    Explanations

    high/low

    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
    olation
    -0.28
    OMEM
    -0.25
    wald
    -0.25
    enstein
    -0.25
    _MUT
    -0.25
    atum
    -0.25
    Invariant
    -0.24
     przec
    -0.24
    çŃł
    -0.23
    ä¹ĭåŁİ
    -0.23
    POSITIVE LOGITS
    ยà¸ģ
    0.28
    åĬ
    0.28
    ä¹°äºĨ
    0.26
     vic
    0.26
    rite
    0.26
    lete
    0.26
    ä¹Łä¸įæĺ¯
    0.25
    isseur
    0.25
    riteria
    0.25
    route
    0.25
    Activations Density 0.003%

    No Known Activations