INDEX

Explanations

appeals

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

dig

-0.28

Dig

-0.28

iban

-0.27

åįĩ

-0.24

@student

-0.24

dig

-0.24

éĩĮçļĦ

-0.24

ä¸ªä¹¡éķĩ

-0.24

éĩĮ

-0.24

ibr

-0.24

POSITIVE LOGITS

moire

0.26

aval

0.25

lik

0.25

ä»¥èī²

0.25

ox

0.25

oise

0.25

 diminishing

0.24

related

0.24

åĿĢ

0.24

HA

0.24

Activations Density 0.006%

appeals

No Comments

No Known Activations