INDEX

Explanations

decision-making

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

åĿļå®Ī

-0.27

ollen

-0.27

about

-0.26

å®Īä½ı

-0.25

åİĭ

-0.25

 Podesta

-0.24

fed

-0.24

éĩįçĤ¹é¢ĨåŁŁ

-0.24

geries

-0.24

å°Ĩç»§ç»Ń

-0.24

POSITIVE LOGITS

Spo

0.29

æĿĥ

0.26

ulti

0.25

è¶Ł

0.24

peg

0.24

spo

0.24

 Blues

0.23

isRequired

0.23

ç¾¡æħķ

0.23

zie

0.23

Activations Density 0.001%

decision-making

No Comments

No Known Activations