INDEX

Explanations

*

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

 Æ¡n

-0.27

å¹´çĶ±

-0.26

æĮĪ

-0.25

åį

-0.24

ä¸»

-0.24

iol

-0.24

Declared

-0.24

 Dahl

-0.24

ç¨ĭåº¦

-0.24

LA

-0.24

POSITIVE LOGITS

æŀ¯çĩ¥

0.27

æ¶¯

0.26

 Tome

0.26

pine

0.26

_algorithm

0.25

ä¸Ģçľĭ

0.25

_alg

0.25

.setViewport

0.25

 Hari

0.25

erializer

0.25

Activations Density 0.092%

*

No Comments

No Known Activations