INDEX

Explanations

markets and sales

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

åĺĺ

-0.28

 After

-0.27

çĹĺ

-0.27

 Astros

-0.25

Synopsis

-0.25

Ell

-0.25

After

-0.24

Detroit

-0.24

after

-0.24

anka

-0.23

POSITIVE LOGITS

åľ°æĿ¿

0.27

ãĤ¿

0.26

 descend

0.26

ovic

0.26

ç´§ç¼º

0.25

illes

0.24

["$

0.24

 Lean

0.24

ALAR

0.24

kommen

0.23

Activations Density 0.025%

markets and sales

No Comments

No Known Activations