INDEX

Explanations

BO

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

autÃ©

-0.29

 naÃ¯

-0.28

shi

-0.26

ä»Ģéº½

-0.26

archical

-0.26

Shr

-0.26

DTD

-0.26

shr

-0.25

pite

-0.25

Ignoring

-0.25

POSITIVE LOGITS

medium

0.28

pline

0.28

 medium

0.26

ä¼į

0.26

 Licensed

0.25

-medium

0.25

uke

0.25

 trays

0.25

inely

0.24

\App

0.24

Activations Density 0.001%

BO

No Comments

No Known Activations