INDEX

Explanations

code and eradication

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

 zach

-0.25

aload

-0.24

leston

-0.24

dump

-0.24

jan

-0.24

 princip

-0.24

lify

-0.23

å¯¹æĬĹ

-0.23

ty

-0.23

 packages

-0.23

POSITIVE LOGITS

ä¸¤é¡¹

0.30

belt

0.28

 Middle

0.27

LABEL

0.26

cooked

0.26

ä¸ĢèĪ¬äºº

0.25

 arithmetic

0.25

arat

0.25

sla

0.25

åĹĳ

0.24

Activations Density 0.039%

code and eradication

No Comments

No Known Activations