INDEX

Explanations

Technical problems

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

éļ³

-0.27

ãĥĬãĤ¤

-0.26

ìĬ¨

-0.25

spots

-0.25

bot

-0.25

.--

-0.24

åĻ¨å®ĺ

-0.24

aiser

-0.23

æĻ¯

-0.23

-hour

-0.23

POSITIVE LOGITS

Tro

0.29

Tro

0.26

aska

0.26

_mo

0.25

 verbally

0.25

tro

0.24

lah

0.24

Raw

0.24

iah

0.23

anka

0.23

Activations Density 0.095%

Technical problems

No Comments

No Known Activations