INDEX

Explanations

code and math

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dif

-0.32

vision

-0.30

inson

-0.29

indo

-0.28

TPL

-0.26

æ¯Ķä¸Ĭå¹´

-0.26

setLayout

-0.25

 Morm

-0.25

 mÃ¹

-0.24

lle

-0.24

POSITIVE LOGITS

 altogether

0.40

 anymore

0.36

æľīä»»ä½ķ

0.34

ä»»ä½ķäºº

0.34

ä»»ä½ķ

0.31

ä»»ä½ķå½¢å¼ı

0.31

 entirely

0.30

any

0.30

any

0.29

 necessarily

0.28

Activations Density 1.564%

code and math

No Comments

No Known Activations