INDEX

Explanations

long-form texts

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

shot

-0.28

 chalk

-0.26

Atlas

-0.26

FIELD

-0.25

 lips

-0.25

é£İåĲ¹

-0.25

 penis

-0.24

.ga

-0.24

è¿Ķä¹¡

-0.23

èĢ½è¯¯

-0.23

POSITIVE LOGITS

eled

0.26

quires

0.26

iamond

0.25

atÃ©g

0.25

 Swords

0.25

 createState

0.25

iÃ³n

0.25

-Requested

0.25

 cuis

0.24

.parseInt

0.24

Activations Density 0.017%

long-form texts

No Comments

No Known Activations