INDEX

Explanations

Informal, conversational writing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĢĲ

-0.26

Cra

-0.24

ç½²

-0.24

 poles

-0.23

ACH

-0.23

 procedural

-0.23

arrera

-0.23

hpp

-0.23

Ø´Ø¨

-0.23

 Scandin

-0.23

POSITIVE LOGITS

æ·¡åĮĸ

0.26

 excell

0.26

Low

0.25

strain

0.25

[Index

0.25

amac

0.24

_Level

0.24

(Level

0.24

æīŃ

0.24

æ°´åĩĨ

0.24

Activations Density 0.001%

Informal, conversational writing

No Comments

No Known Activations