INDEX

Explanations

answering questions

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

 answers

-0.35

.answers

-0.34

çļĦçŃĶæ¡Ī

-0.34

Answers

-0.31

_answers

-0.30

 Answers

-0.30

ç»ĵ

-0.29

answers

-0.29

è¡£

-0.28

iram

-0.28

POSITIVE LOGITS

èĩĢ

0.30

(dot

0.27

acent

0.26

 Cast

0.26

 SERIAL

0.26

 sucker

0.25

 Snyder

0.24

.configuration

0.24

.Cast

0.24

-vis

0.24

Activations Density 0.037%

answering questions

No Comments

No Known Activations