INDEX

Explanations

Repetition

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

communication

-0.26

å¯¹ä½ł

-0.26

å¯¹æĪĳ

-0.25

å¯¹æĪĳä»¬

-0.25

åłĨ

-0.25

æĶ¾æīĭ

-0.25

charts

-0.25

usch

-0.24

DevExpress

-0.24

"""),↵

-0.24

POSITIVE LOGITS

 repeat

0.28

loud

0.28

 repeats

0.28

ÙħØ¯

0.28

PLICATE

0.28

éĩįå¤į

0.27

 duplicates

0.26

dur

0.26

 Repeat

0.26

çĽĳäºĭ

0.25

Activations Density 0.255%

Repetition

No Comments

No Known Activations