INDEX

Explanations

bo

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tractor

-0.31

iot

-0.30

ourg

-0.28

èİ«æĸ¯

-0.28

çī©

-0.27

ApplicationBuilder

-0.27

ãĥĳãĥ¼ãĥĪ

-0.26

 pinch

-0.26

ìłĪ

-0.26

ENER

-0.25

POSITIVE LOGITS

 Terr

0.28

æĴ¥

0.28

çº¶

0.27

Rhe

0.26

prene

0.26

serialized

0.25

 Winds

0.25

Terr

0.25

owane

0.24

å¢ŀåĢ¼

0.24

Activations Density 0.111%

bo

No Comments

No Known Activations