INDEX

Explanations

forget

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

 wrest

-0.26

 Compilation

-0.25

 shading

-0.25

ç¥ķ

-0.25

Warnings

-0.24

ç§ĺ

-0.24

ä½ĥ

-0.24

 parity

-0.23

 jobId

-0.23

tk

-0.23

POSITIVE LOGITS

è¶³

0.30

ä¸ĢæĶ¯

0.27

pNet

0.26

å®¶è£ħ

0.26

æĶ¹è¿Ľ

0.26

éĢļå¸¸æĺ¯

0.25

enti

0.25

åı¯çĶ¨

0.24

ä¸Ģä¼ļ

0.24

æĿĨ

0.24

Activations Density 0.002%

forget

No Comments

No Known Activations