INDEX

Explanations

IV

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵↵↵↵↵↵

-0.27

↵↵↵↵↵↵↵↵↵

-0.27

grow

-0.26

éĩ

-0.25

amo

-0.24

agra

-0.24

uilder

-0.24

 invis

-0.24

 blocker

-0.24

 billion

-0.23

POSITIVE LOGITS

-syntax

0.26

 Pending

0.26

ichte

0.25

 Cong

0.25

uvw

0.25

 tonight

0.25

RAINT

0.25

 Attached

0.25

raise

0.25

èħ®

0.24

Activations Density 0.028%

IV

No Comments

No Known Activations