INDEX

Explanations

Roger

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

 clashes

-0.27

é©¬æĭī

-0.26

çħ³

-0.26

PROP

-0.25

åİī

-0.24

GRP

-0.24

 chá»©

-0.24

çļĦå¹´è½»äºº

-0.24

åįİæ¶¦

-0.24

 Andy

-0.23

POSITIVE LOGITS

 orbit

0.28

Pot

0.27

ociety

0.26

çīĮ

0.26

çĶ»

0.26

buffer

0.26

Pot

0.26

æį¢ä¸ª

0.26

Mit

0.25

ä¸»æĦı

0.25

Activations Density 0.784%

Roger

No Comments

No Known Activations