INDEX

Explanations

way, direction

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

rollable

-0.31

 repeat

-0.30

 Repeat

-0.28

ndx

-0.27

çī¹èī²

-0.26

repeat

-0.26

phas

-0.26

å®¢

-0.26

 standard

-0.26

abet

-0.26

POSITIVE LOGITS

uating

0.27

çģ«çĤ¬

0.25

åĩºå±Ģ

0.24

fork

0.24

dto

0.24

gre

0.24

gel

0.24

 Kirby

0.23

å¼ķçĪĨ

0.23

æ©Ħæ¦Ħ

0.23

Activations Density 0.006%

way, direction

No Comments

No Known Activations