INDEX

Explanations

of

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

 PROT

-0.26

oggled

-0.26

scenario

-0.26

 stere

-0.25

uber

-0.25

å°ĸåı«

-0.25

hood

-0.25

å¥³åĦ¿

-0.24

ritten

-0.24

 InputStreamReader

-0.23

POSITIVE LOGITS

edis

0.29

æľĢå°ĳ

0.28

 Ahead

0.26

ç»Ļä½łä»¬

0.26

 flex

0.26

cot

0.26

pson

0.25

 least

0.25

æ²¡åķ¥

0.25

ham

0.24

Activations Density 0.001%

of

No Comments

No Known Activations