INDEX

Explanations

and

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

 intersections

-0.27

 IMPLIED

-0.26

 Sawyer

-0.25

è®°è½½

-0.25

TERN

-0.25

proc

-0.25

 Amendments

-0.25

çĶ³è¯·

-0.24

.mat

-0.24

äº¤åıī

-0.24

POSITIVE LOGITS

elite

0.28

meaning

0.25

Ãªu

0.24

 didFinish

0.24

çļĦä»·æł¼

0.24

ħ§

0.24

é¦ĸå®¶

0.24

elson

0.24

utch

0.23

çļĦæĪĲæľ¬

0.23

Activations Density 0.002%

and

No Comments

No Known Activations