INDEX

Explanations

plus sign

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

room

-0.28

 room

-0.25

(room

-0.25

åģıåĲĳ

-0.24

ç¤¾åĮº

-0.24

 puzzle

-0.24

imm

-0.24

ä¸įåĩĨ

-0.23

omi

-0.23

ationToken

-0.23

POSITIVE LOGITS

sha

0.29

è°ı

0.28

 bond

0.27

âį¨

0.27

_bind

0.25

è¯°

0.24

gh

0.24

gon

0.24

USH

0.23

ÑģÐ¾Ð»

0.23

Activations Density 0.010%

plus sign

No Comments

No Known Activations