INDEX

Explanations

protect

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

å¥¥æĸ¯

-0.28

Lens

-0.28

_lens

-0.25

 Nets

-0.25

 Pull

-0.25

ÑĢÐ¾Ñģ

-0.24

 Ramsey

-0.24

æĻ®

-0.24

éķ¿çĽ¸

-0.24

inel

-0.24

POSITIVE LOGITS

InstanceId

0.25

MOST

0.25

mort

0.25

>C

0.24

 gifs

0.24

åıĹ

0.24

å¤ºåĨł

0.24

ç«¶

0.24

äºı

0.24

_>

0.24

Activations Density 0.039%

protect

No Comments

No Known Activations