© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161665
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .GetObject
    -0.29
    çŁ³å®¶
    -0.28
    åľ°
    -0.26
    _oid
    -0.26
    istrate
    -0.25
    iban
    -0.25
    AtPath
    -0.24
    objs
    -0.24
    PageRoute
    -0.24
    _fsm
    -0.24
    POSITIVE LOGITS
    unting
    0.29
    æĺ¯åĽ½åĨħ
    0.28
     beard
    0.26
    imar
    0.25
     basically
    0.25
     Kill
    0.24
    缮åīįåĽ½åĨħ
    0.24
    imately
    0.24
    伤
    0.24
    çļĦæ¶Īæģ¯
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.