INDEX

Explanations

this

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

dep

-0.32

deps

-0.29

eness

-0.28

odal

-0.27

Dep

-0.26

éĹ®ä»ĸ

-0.26

 edges

-0.26

dep

-0.25

ost

-0.25

ÑģÐºÐ¾Ð¿

-0.25

POSITIVE LOGITS

cry

0.27

 khÃ¡ng

0.25

perse

0.25

 rematch

0.25

 arrayOf

0.24

ToFit

0.24

anian

0.24

pak

0.24

å¥½çľĭçļĦ

0.24

å¾Ļ

0.24

Activations Density 0.003%

this

No Comments

No Known Activations