INDEX

Explanations

Parenthetical remarks

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

ev

-0.29

EV

-0.28

SFML

-0.27

_ev

-0.27

place

-0.25

ä¹ĭæīĢ

-0.25

æŃ·åı²

-0.25

Ã³j

-0.24

eel

-0.24

ee

-0.24

POSITIVE LOGITS

ury

0.27

Ð³Ð¾Ð½

0.26

 Wool

0.26

zar

0.24

 chromat

0.24

èĬĴ

0.24

çĶĺ

0.24

-ion

0.24

jem

0.24

jis

0.24

Activations Density 46.072%

Parenthetical remarks

No Comments

No Known Activations