INDEX

Explanations

Punctuation and filler

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çĵ·

-0.27

 Kramer

-0.26

alloc

-0.25

åıĮåĲĳ

-0.25

 excess

-0.25

çļĩé©¬

-0.24

æľ¬èº«

-0.24

éĸĴ

-0.23

pherical

-0.23

LOOK

-0.23

POSITIVE LOGITS

éĻĽ

0.25

 Ð´Ð¾Ð±

0.25

orian

0.25

ukes

0.24

 Swamp

0.24

è

0.24

æĴ°

0.24

curacy

0.24

ä¿®æĶ¹

0.24

éģ¥

0.23

Activations Density 0.106%

Punctuation and filler

No Comments

No Known Activations