INDEX

Explanations

comparisons and conditions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 adviser

-0.28

çķ¸

-0.28

ansas

-0.27

è¾ķ

-0.26

 Scheme

-0.25

ONG

-0.25

 memorandum

-0.25

 anchors

-0.25

åĽ´

-0.25

 whales

-0.24

POSITIVE LOGITS

TION

0.27

éĹ´éļĶ

0.26

-ins

0.25

ç§ĳåĪĽæĿ¿

0.24

 insert

0.24

ossa

0.24

æĬľãģĳ

0.24

è¥¿æ¹ĸ

0.24

_hat

0.24

ented

0.24

Activations Density 0.131%

comparisons and conditions

No Comments

No Known Activations