INDEX

Explanations

BASIS

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

 volley

-0.27

æĪİ

-0.26

ays

-0.26

mapper

-0.25

èĢħçļĦ

-0.25

mans

-0.25

 QUICK

-0.24

rette

-0.24

ãģ¹

-0.24

 taco

-0.24

POSITIVE LOGITS

 Garage

0.31

Gol

0.29

 Pred

0.28

 Karnataka

0.28

æķ¬

0.27

è¾ľ

0.26

åĺĮ

0.26

éķ¿å¯¿

0.26

 achter

0.26

DESCRIPTION

0.25

Activations Density 0.009%

BASIS

No Comments

No Known Activations