INDEX

Explanations

guide

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

åħ¬å¼ı

-0.25

opia

-0.25

 formula

-0.25

èµ°åĪ°

-0.25

enaire

-0.25

äº§ä¸ļåĮĸ

-0.25

åŃª

-0.24

enen

-0.24

åħļé£İ

-0.24

sc

-0.24

POSITIVE LOGITS

 STRICT

0.26

EditMode

0.25

 Strict

0.25

åĹ¡

0.25

å¤ªé«ĺ

0.25

Strict

0.24

.realm

0.24

 mell

0.24

urs

0.24

è¶Ĭ

0.24

Activations Density 0.090%

guide

No Comments

No Known Activations