© 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. 23-TRANSCODER-HP
    7. 163500
    Prev
    Next
    INDEX
    Explanations

    Searching or intending

    np_max-act · gemini-2.0-flash
    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
    ä¸įåłª
    -0.31
    bridge
    -0.28
    alle
    -0.28
     optional
    -0.28
    iris
    -0.27
    被迫
    -0.27
    对çħ§
    -0.27
    åħ±
    -0.26
    ocop
    -0.26
    æĹłæķĪ
    -0.26
    POSITIVE LOGITS
    izados
    0.30
    lijk
    0.28
    AlgorithmException
    0.27
    itant
    0.26
    ç»Ī身
    0.25
    atro
    0.25
    izado
    0.24
    ablish
    0.24
    à¸ļาย
    0.24
     JUST
    0.23
    Activations Density 0.016%

    No Known Activations