INDEX

Explanations

Progress, stages, or time

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

 needle

-0.29

azione

-0.27

ilet

-0.26

åħ¬å¹³

-0.26

é³ŀ

-0.25

lices

-0.25

Wheel

-0.24

åĲĮäºĭä»¬

-0.24

â½´

-0.24

æ¯¡

-0.24

POSITIVE LOGITS

oracle

0.30

suite

0.28

antine

0.26

pta

0.26

è·

0.25

emin

0.25

RecognitionException

0.24

é¥®çĶ¨æ°´

0.24

 abide

0.24

ccount

0.24

Activations Density 0.028%

Progress, stages, or time

No Comments

No Known Activations