INDEX

Explanations

technical/scientific text

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

 Surge

-0.26

ä¾£

-0.26

theory

-0.26

èķ¨

-0.26

è¿Ļæī¹

-0.26

-inverse

-0.26

presence

-0.26

 Ð½Ð°Ð»Ð¸Ñĩ

-0.26

éľ°

-0.26

 replic

-0.25

POSITIVE LOGITS

_baseline

0.28

 baseline

0.28

 additive

0.27

Add

0.27

äº¤æĺĵä¸Ńå¿ĥ

0.27

Add

0.26

baseline

0.25

Credentials

0.25

 ifndef

0.25

ä¸ŃåİŁ

0.25

Activations Density 0.297%

technical/scientific text

No Comments

No Known Activations