INDEX

Explanations

organs

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

ableView

-0.28

bur

-0.26

ory

-0.26

obil

-0.26

Bol

-0.25

ya

-0.25

XA

-0.25

Cache

-0.25

ackle

-0.25

ÑģÐºÐ°

-0.24

POSITIVE LOGITS

åµ´

0.31

å¸ĺ

0.30

Wit

0.30

åªĴ

0.30

ÑĨÐ¸Ð½

0.28

([{

0.27

 misconception

0.26

rypton

0.26

GetPosition

0.26

yna

0.26

Activations Density 0.012%

organs

No Comments

No Known Activations