INDEX

Explanations

lifestyle

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

 animal

-0.27

æĴµ

-0.26

 installment

-0.26

ķĮ

-0.26

æĭŃ

-0.25

%@

-0.25

exclusive

-0.25

å®¶

-0.25

 conversions

-0.25

 succeeding

-0.24

POSITIVE LOGITS

rah

0.28

.sort

0.27

urat

0.25

æ²ħ

0.25

-den

0.25

å²ĺ

0.25

è¯Ħ

0.25

odes

0.25

æĦıæĦ¿

0.25

.emit

0.24

Activations Density 0.001%

lifestyle

No Comments

No Known Activations