INDEX

Explanations

ret

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

åĽĬ

-0.28

fits

-0.27

_tabs

-0.26

plits

-0.25

arium

-0.25

icles

-0.25

Tabs

-0.25

éĤº

-0.24

èĲ§

-0.24

 Selected

-0.24

POSITIVE LOGITS

manifest

0.26

 verv

0.25

leh

0.24

.CommandType

0.24

 regress

0.24

spot

0.24

amiliar

0.24

å¥łåŁº

0.24

ripe

0.24

assy

0.24

Activations Density 0.454%

ret

No Comments

No Known Activations