INDEX

Explanations

machine

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

SQLException

-0.27

esian

-0.25

ecn

-0.25

äº²

-0.25

 spherical

-0.25

SQL

-0.25

morph

-0.24

eca

-0.23

å¹²çĩ¥

-0.23

çĲĥ

-0.23

POSITIVE LOGITS

Equality

0.27

èµ·èº«

0.27

å°Ħ

0.25

-Cs

0.25

çģŃ

0.25

lds

0.25

è¡ĢèĦī

0.24

ãĥĿãĤ¤

0.24

plies

0.24

 Explos

0.24

Activations Density 0.030%

machine

No Comments

No Known Activations