INDEX

Explanations

a

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

HELL

-0.28

-0.27

 Every

-0.27

ment

-0.26

è©

-0.25

Ð·Ð°Ð²

-0.25

 shell

-0.25

çī¹æ®ĬçļĦ

-0.25

 plan

-0.24

 every

-0.24

POSITIVE LOGITS

éĴī

0.27

åĨ³èĥľ

0.26

 Slim

0.25

.share

0.25

digest

0.25

æ¸ħæĸ°

0.25

éħ¥

0.25

 Freedom

0.24

PO

0.24

aban

0.24

Activations Density 0.001%

a

No Comments

No Known Activations