© 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. 163818
    Prev
    Next
    INDEX
    Explanations

    still

    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
     flags
    -0.26
     criter
    -0.25
    ç½¢äºĨ
    -0.25
    ç»Ħ
    -0.25
     omission
    -0.24
     as
    -0.24
    éĻ¤
    -0.24
     autom
    -0.24
     vs
    -0.24
    allest
    -0.23
    POSITIVE LOGITS
    olley
    0.30
     articulate
    0.27
    ioxid
    0.26
    è¿İ
    0.26
    Reverse
    0.26
    thenReturn
    0.26
    zÄħ
    0.26
    anga
    0.25
     reverse
    0.25
    ä¸Ģ身
    0.25
    Activations Density 0.005%

    No Known Activations