INDEX

Explanations

,

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.solution

-0.30

è§£åĨ³æĸ¹æ¡Ī

-0.30

 solutions

-0.30

 solution

-0.28

åį´è¢«

-0.27

mts

-0.27

è§£åĨ³éĹ®é¢ĺ

-0.26

è¿ĻäºĽéĹ®é¢ĺ

-0.26

erek

-0.25

 solves

-0.25

POSITIVE LOGITS

usage

0.27

ä½¿çĶ¨æĿĥ

0.26

 plant

0.26

ely

0.25

 Einsatz

0.25

udent

0.25

 fame

0.25

åĬŁåĬ³

0.25

irut

0.24

 Usage

0.24

Activations Density 0.021%

,

No Comments

No Known Activations