INDEX

Explanations

excerpt

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

ucher

-0.35

inne

-0.29

stalk

-0.29

ichi

-0.27

éĴĩ

-0.27

çŀ

-0.26

INDER

-0.25

æĢµ

-0.24

allet

-0.24

usk

-0.24

POSITIVE LOGITS

lin

0.28

erg

0.25

 prol

0.25

 Presidency

0.25

 birthday

0.25

FIT

0.24

å¸¸å¸¸

0.24

ÙĦØ¨

0.24

æŁ³

0.23

intValue

0.23

Activations Density 0.055%

excerpt

No Comments

No Known Activations