INDEX

Explanations

rapid change

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

å¼ķçĶ¨

-0.25

_stderr

-0.25

OV

-0.24

Lov

-0.24

OV

-0.24

loading

-0.23

 poverty

-0.23

 loading

-0.23

 incomes

-0.23

 rval

-0.23

POSITIVE LOGITS

áº¡ng

0.30

 york

0.26

-du

0.25

æĭ¬

0.25

 Ezek

0.24

æ¨Ĭ

0.24

å¤§åħ¨

0.24

falls

0.23

åıĳå±ķéĺ¶æ®µ

0.23

ìĶ¨

0.23

Activations Density 1.146%

rapid change

No Known Activations