INDEX

Explanations

Code, links, and foreign languages

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

perate

-0.29

cke

-0.27

rangle

-0.27

Ð±ÐµÑĢ

-0.25

 BASIS

-0.25

èĬĴ

-0.24

otle

-0.24

 arrang

-0.24

vae

-0.24

æ¸¤

-0.23

POSITIVE LOGITS

IV

0.28

III

0.27

çĿĢä»ĸ

0.26

åĿ»

0.26

IV

0.25

MQ

0.24

stringValue

0.24

.son

0.24

ATM

0.24

Sm

0.23

Activations Density 0.790%

Code, links, and foreign languages

No Comments

No Known Activations