INDEX

Explanations

resources, datasets, code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thal

-0.27

ç¾¤

-0.26

ä¸»åĬ¨

-0.26

 Embed

-0.26

ihu

-0.25

.Embed

-0.25

lover

-0.25

å§Ĳå¦¹

-0.25

legate

-0.24

 guest

-0.24

POSITIVE LOGITS

imat

0.26

è¯ģ

0.26

èŃī

0.25

-ret

0.25

 behind

0.25

å¥½è±¡

0.24

è¯ģä»¶

0.24

è¿ĺæĥ³

0.23

åĺ¿

0.23

æĬķæĶ¾

0.23

Activations Density 0.001%

resources, datasets, code

No Comments

No Known Activations