INDEX

Explanations

internet excerpts

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

OMEM

-0.33

lse

-0.28

Ã§os

-0.27

leases

-0.26

contracts

-0.25

æµ¯

-0.25

HEMA

-0.25

ÐµÐ´

-0.24

orest

-0.24

actual

-0.24

POSITIVE LOGITS

equ

0.26

å½ĵåľº

0.25

peri

0.25

tuple

0.25

é¢ĦæĬ¥

0.25

ë²Į

0.24

tool

0.24

 extrapol

0.24

 Cartesian

0.24

åİĭåĪ¶

0.23

Activations Density 0.011%

internet excerpts

No Comments

No Known Activations