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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5463
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åīģ
    -0.27
    _MR
    -0.25
     cram
    -0.24
     củ
    -0.23
    äºīåıĸ
    -0.23
    LEM
    -0.23
     brun
    -0.23
    ãĤ°ãĥ«
    -0.23
    .trim
    -0.23
    (gp
    -0.23
    POSITIVE LOGITS
     sim
    0.30
    sim
    0.30
    çĨŁ
    0.29
    干线
    0.26
    è¶Ĭå¤ļ
    0.26
     Sim
    0.26
    æ¯ĶæĪij
    0.25
    ãģ»ãģ©
    0.25
    atype
    0.25
    .sim
    0.25
    Activations Density 0.033%

    No Known Activations

    This feature has no known activations.