INDEX

Explanations

Incremental change or comparison

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

 scholar

-0.30

cis

-0.29

éĽ¾

-0.28

 Scholar

-0.27

èĥ½åĬĽå¼º

-0.26

cht

-0.26

zie

-0.25

åŃ¦èĢħ

-0.25

RAD

-0.24

..'

-0.24

POSITIVE LOGITS

bev

0.27

ecera

0.26

 Lahore

0.25

é½¡

0.24

utoff

0.23

TeV

0.23

 sammen

0.23

apot

0.23

eti

0.23

.Headers

0.23

Activations Density 0.002%

Incremental change or comparison

No Comments

No Known Activations