INDEX

Explanations

ha

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wrapper

-0.28

 amongst

-0.25

 Boiler

-0.25

 ÑĤÐ¾Ð²Ð°ÑĢ

-0.25

 wrapper

-0.24

çĴ§

-0.24

ueue

-0.24

UNITY

-0.24

çĶŁäº§åĴĮ

-0.24

_,↵

-0.24

POSITIVE LOGITS

å¾ħ

0.29

mid

0.27

ç»ľ

0.26

èĦĬ

0.26

åµ´

0.26

sc

0.25

hem

0.25

å±Ī

0.25

AIM

0.25

 TRACE

0.25

Activations Density 0.786%

ha

No Comments

No Known Activations