INDEX

Explanations

while

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 besser

-0.27

 mxArray

-0.26

èĤ¤

-0.26

 plat

-0.25

ltk

-0.25

 descent

-0.25

ãģ¨ãģĦãģ£ãģ¦ãĤĤ

-0.25

fuse

-0.24

 Shuttle

-0.24

çĺģ

-0.24

POSITIVE LOGITS

emens

0.34

 Modi

0.27

ulas

0.27

yy

0.27

åıĸæ¶Ī

0.26

uteur

0.25

IRA

0.25

utive

0.25

 enough

0.24

omm

0.24

Activations Density 0.004%

while

No Comments

No Known Activations