INDEX

Explanations

cause

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

 again

-0.31

 race

-0.27

Again

-0.27

again

-0.27

åĲĮä¸ļ

-0.26

ç«Ļåľ¨

-0.26

 Again

-0.25

ge

-0.25

Resolve

-0.25

/Private

-0.25

POSITIVE LOGITS

reh

0.28

LOC

0.26

EMU

0.26

hq

0.26

perature

0.25

ibia

0.24

ENTA

0.24

å®ļä½į

0.24

errs

0.23

 plank

0.23

Activations Density 0.011%

cause

No Comments

No Known Activations