INDEX

Explanations

However

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iones

-0.31

atre

-0.26

bugs

-0.25

ä¸Ģä¼ļ

-0.24

uckles

-0.24

ãĥĪãĥª

-0.24

å¤§åıĳ

-0.24

ASI

-0.24

 Trails

-0.24

agram

-0.23

POSITIVE LOGITS

RuleContext

0.28

roach

0.28

 leven

0.26

tic

0.25

å§ĭäºİ

0.25

@student

0.25

åĬĽ

0.24

å½¢å®¹

0.24

çı¾åł´

0.24

åĲĳçĿĢ

0.24

Activations Density 0.001%

However

No Comments

No Known Activations