INDEX

Explanations

the

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

omics

-0.29

ç¬¦

-0.27

çļĦæĪ¿åŃĲ

-0.26

CompleteListener

-0.26

Total

-0.25

áº¡

-0.24

é¢ĦæľŁ

-0.24

aim

-0.24

Ð¿Ð¾ÑĤ

-0.24

 testing

-0.24

POSITIVE LOGITS

 authDomain

0.31

jal

0.27

 revolt

0.27

attro

0.26

Åĺ

0.26

ahren

0.26

å³¡

0.26

çº§ä»¥ä¸Ĭ

0.26

TPM

0.25

lut

0.25

Activations Density 0.024%

the

No Comments

No Known Activations