INDEX

Explanations

Text excerpts

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

åĪĨåĪ¥

-0.28

èĬ±å¼Ģ

-0.27

å¸Ŀ

-0.26

æį¢ä¸ª

-0.25

 Grat

-0.25

,filename

-0.25

Fry

-0.24

åĪĨåĪ«

-0.24

uche

-0.24

ä¸ĵä¸ļçŁ¥è¯Ĩ

-0.24

POSITIVE LOGITS

quam

0.29

æĪĳè¿ĺæĺ¯

0.28

éĶ»

0.26

èŀ³

0.25

 blow

0.24

 room

0.24

old

0.24

stab

0.24

scopic

0.24

Activations Density 0.001%

Text excerpts

No Comments

No Known Activations