INDEX

Explanations

finding

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_10.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.10.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

es

-0.28

-0.26

 they

-0.26

åİĭç¼©

-0.25

ii

-0.25

pr

-0.25

ES

-0.25

 Ð´Ð¸ÑĢ

-0.25

 headed

-0.24

.org

-0.24

POSITIVE LOGITS

ä¸įç¨³å®ļ

0.32

izio

0.30

 Liberia

0.28

èĿĩ

0.28

ÑģÑĤÑĢÐ¾Ð¸ÑĤÐµÐ»ÑĮ

0.25

çĸ«

0.25

itionally

0.25

odef

0.24

Pot

0.24

ç²Ĺ

0.24

Activations Density 0.009%

finding

No Comments

No Known Activations

finding

No Comments

No Known Activations